diff --git a/optional-skills/blockchain/evm/SKILL.md b/optional-skills/blockchain/evm/SKILL.md
index 989d59509f338..039f1d7da8a8c 100644
--- a/optional-skills/blockchain/evm/SKILL.md
+++ b/optional-skills/blockchain/evm/SKILL.md
@@ -66,40 +66,40 @@ Helper script path: `~/.hermes/skills/blockchain/evm/scripts/evm_client.py`
 SCRIPT=~/.hermes/skills/blockchain/evm/scripts/evm_client.py
 
 # Network & prices
-python3 $SCRIPT stats                            # Ethereum stats
-python3 $SCRIPT stats --chain arbitrum           # Arbitrum stats
-python3 $SCRIPT compare                          # Gas + prices ALL 8 chains
+python $SCRIPT stats                            # Ethereum stats
+python $SCRIPT stats --chain arbitrum           # Arbitrum stats
+python $SCRIPT compare                          # Gas + prices ALL 8 chains
 
 # Wallet
-python3 $SCRIPT wallet 0xd8dA...96045            # Portfolio (ETH + ERC-20)
-python3 $SCRIPT wallet 0xd8dA...96045 --chain bsc
-python3 $SCRIPT multichain 0xd8dA...96045        # Same wallet on ALL chains
+python $SCRIPT wallet 0xd8dA...96045            # Portfolio (ETH + ERC-20)
+python $SCRIPT wallet 0xd8dA...96045 --chain bsc
+python $SCRIPT multichain 0xd8dA...96045        # Same wallet on ALL chains
 
 # Tokens & prices
-python3 $SCRIPT price ETH
-python3 $SCRIPT price 0xdAC1...1ec7              # By contract address
-python3 $SCRIPT token 0xdAC1...1ec7              # ERC-20 metadata + market cap
+python $SCRIPT price ETH
+python $SCRIPT price 0xdAC1...1ec7              # By contract address
+python $SCRIPT token 0xdAC1...1ec7              # ERC-20 metadata + market cap
 
 # Transactions
-python3 $SCRIPT tx 0x5c50...f060                 # Transaction details
-python3 $SCRIPT decode 0x5c50...f060             # Decode input data (4byte.directory)
-python3 $SCRIPT activity 0xd8dA...96045          # Recent transactions
+python $SCRIPT tx 0x5c50...f060                 # Transaction details
+python $SCRIPT decode 0x5c50...f060             # Decode input data (4byte.directory)
+python $SCRIPT activity 0xd8dA...96045          # Recent transactions
 
 # Gas
-python3 $SCRIPT gas                              # Gas prices + cost estimates
-python3 $SCRIPT gas --chain optimism
+python $SCRIPT gas                              # Gas prices + cost estimates
+python $SCRIPT gas --chain optimism
 
 # Security
-python3 $SCRIPT allowance 0xd8dA...96045         # Dangerous ERC-20 approvals
-python3 $SCRIPT contract 0xdAC1...1ec7           # Contract inspection (proxy? standards?)
+python $SCRIPT allowance 0xd8dA...96045         # Dangerous ERC-20 approvals
+python $SCRIPT contract 0xdAC1...1ec7           # Contract inspection (proxy? standards?)
 
 # ENS
-python3 $SCRIPT ens vitalik.eth                  # Name -> address + profile
-python3 $SCRIPT ens 0xd8dA...96045               # Address -> ENS name
+python $SCRIPT ens vitalik.eth                  # Name -> address + profile
+python $SCRIPT ens 0xd8dA...96045               # Address -> ENS name
 
 # Whale detection
-python3 $SCRIPT whale                            # Large transfers (last 20 blocks, >$10k)
-python3 $SCRIPT whale --blocks 50 --min-usd 100000 --chain arbitrum
+python $SCRIPT whale                            # Large transfers (last 20 blocks, >$10k)
+python $SCRIPT whale --blocks 50 --min-usd 100000 --chain arbitrum
 ```
 
 ---
@@ -108,67 +108,67 @@ python3 $SCRIPT whale --blocks 50 --min-usd 100000 --chain arbitrum
 
 ### 0. Setup Check
 ```bash
-python3 --version   # 3.8+ required
-python3 ~/.hermes/skills/blockchain/evm/scripts/evm_client.py stats
+python --version   # 3.8+ required
+python ~/.hermes/skills/blockchain/evm/scripts/evm_client.py stats
 ```
 
 ### 1. Wallet Portfolio
 Native balance + known ERC-20 tokens, sorted by USD value.
 ```bash
-python3 $SCRIPT wallet 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045
-python3 $SCRIPT wallet 0xd8dA... --chain bsc --no-prices   # faster
+python $SCRIPT wallet 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045
+python $SCRIPT wallet 0xd8dA... --chain bsc --no-prices   # faster
 ```
 
 ### 2. Multi-Chain Scan
 Scans all 8 chains simultaneously for the same address using threads.
 ```bash
-python3 $SCRIPT multichain 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045
+python $SCRIPT multichain 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045
 ```
 Output: per-chain native balance + token holdings + grand total USD.
 
 ### 3. Compare (Gas + Prices)
 All 8 chains queried in parallel. Shows cheapest/most expensive chain.
 ```bash
-python3 $SCRIPT compare
+python $SCRIPT compare
 ```
 
 ### 4. Transaction Details & Decode
 ```bash
-python3 $SCRIPT tx 0x5c504ed432cb51138bcf09aa5e8a410dd4a1e204ef84bfed1be16dfba1b22060
-python3 $SCRIPT decode 0x5c504ed...   # Shows human-readable function signature
+python $SCRIPT tx 0x5c504ed432cb51138bcf09aa5e8a410dd4a1e204ef84bfed1be16dfba1b22060
+python $SCRIPT decode 0x5c504ed...   # Shows human-readable function signature
 ```
 Decode uses 4byte.directory to translate 0xa9059cbb -> transfer(address,uint256).
 
 ### 5. ENS Resolution
 ```bash
-python3 $SCRIPT ens vitalik.eth          # -> 0xd8dA... + avatar + social links
-python3 $SCRIPT ens 0xd8dA...96045       # -> vitalik.eth
+python $SCRIPT ens vitalik.eth          # -> 0xd8dA... + avatar + social links
+python $SCRIPT ens 0xd8dA...96045       # -> vitalik.eth
 ```
 
 ### 6. Allowance Checker (Security)
 Checks ERC-20 approvals granted to known DEX/bridge contracts.
 ```bash
-python3 $SCRIPT allowance 0xYourWallet
+python $SCRIPT allowance 0xYourWallet
 ```
 Flags UNLIMITED approvals as HIGH risk.
 
 ### 7. Contract Inspector
 ```bash
-python3 $SCRIPT contract 0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48   # USDC (proxy)
-python3 $SCRIPT contract 0xdAC17F958D2ee523a2206206994597C13D831ec7   # USDT (ERC-20)
+python $SCRIPT contract 0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48   # USDC (proxy)
+python $SCRIPT contract 0xdAC17F958D2ee523a2206206994597C13D831ec7   # USDT (ERC-20)
 ```
 Detects: proxy (EIP-1967/EIP-1167), ERC-20, ERC-721, ERC-165. Shows bytecode size and implementation address for proxies.
 
 ### 8. Whale Detection
 ```bash
-python3 $SCRIPT whale                                    # ETH, last 20 blocks, >$10k
-python3 $SCRIPT whale --blocks 50 --min-usd 50000 --chain bsc
+python $SCRIPT whale                                    # ETH, last 20 blocks, >$10k
+python $SCRIPT whale --blocks 50 --min-usd 50000 --chain bsc
 ```
 
 ### 9. Gas Tracker
 ```bash
-python3 $SCRIPT gas
-python3 $SCRIPT gas --chain polygon
+python $SCRIPT gas
+python $SCRIPT gas --chain polygon
 ```
 Shows gwei price + USD cost for: transfer, ERC-20 transfer, approve, swap, NFT mint, NFT transfer.
 
@@ -204,8 +204,8 @@ Shows gwei price + USD cost for: transfer, ERC-20 transfer, approve, swap, NFT m
 ## Verification
 ```bash
 # Should print current block, gas price, ETH price
-python3 ~/.hermes/skills/blockchain/evm/scripts/evm_client.py stats
+python ~/.hermes/skills/blockchain/evm/scripts/evm_client.py stats
 
 # Should resolve vitalik.eth to 0xd8dA...
-python3 ~/.hermes/skills/blockchain/evm/scripts/evm_client.py ens vitalik.eth
+python ~/.hermes/skills/blockchain/evm/scripts/evm_client.py ens vitalik.eth
 ```
diff --git a/optional-skills/blockchain/hyperliquid/SKILL.md b/optional-skills/blockchain/hyperliquid/SKILL.md
index 51843bbf1b341..56dc737d13548 100644
--- a/optional-skills/blockchain/hyperliquid/SKILL.md
+++ b/optional-skills/blockchain/hyperliquid/SKILL.md
@@ -55,7 +55,7 @@ Helper script: `~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_clie
 Invoke through the `terminal` tool:
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py <command> [args]
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py <command> [args]
 ```
 
 Add `--json` to any command for machine-readable output.
@@ -89,12 +89,12 @@ optional when `HYPERLIQUID_USER_ADDRESS` is set in `${HERMES_HOME:-~/.hermes}/.e
 ### 1. Discover DEXs and Markets
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py dexs
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py dexs
 
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   markets --limit 15 --sort volume
 
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   spots --limit 15
 ```
 
@@ -105,10 +105,10 @@ python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
 ### 2. Pull Historical Market Data
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   candles BTC --interval 1h --hours 72 --limit 48
 
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   funding BTC --hours 168 --limit 30
 ```
 
@@ -118,7 +118,7 @@ Time-range endpoints paginate. For larger windows, repeat with a later
 ### 3. Inspect Live Order Book
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   l2 BTC --levels 10
 ```
 
@@ -128,10 +128,10 @@ impact of a large order.
 ### 4. Review an Account
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   state 0xabc...
 
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   spot-balances
 ```
 
@@ -142,20 +142,20 @@ withdrawable?".
 ### 5. Review Fills and Orders
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   fills 0xabc... --hours 72 --limit 25
 
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   orders --limit 25
 ```
 
 ### 6. Generate a Trade Review
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   review 0xabc... --hours 72 --fills 50
 
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   review --coin BTC --hours 168
 ```
 
@@ -171,10 +171,10 @@ from outcome quality.
 ### 7. Export a Reusable Dataset
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   export BTC --interval 1h --hours 168 --output ./btc-1h-7d.json
 
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   export BTC --interval 15m --hours 72 --end-time-ms 1760000000000
 ```
 
@@ -204,7 +204,7 @@ normalized candle rows, normalized funding rows, summary stats. Use
 ## Verification
 
 ```bash
-python3 ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
+python ~/.hermes/skills/blockchain/hyperliquid/scripts/hyperliquid_client.py \
   markets --limit 5
 ```
 
diff --git a/optional-skills/blockchain/solana/SKILL.md b/optional-skills/blockchain/solana/SKILL.md
index 9da954f7de4cd..37536c80f865b 100644
--- a/optional-skills/blockchain/solana/SKILL.md
+++ b/optional-skills/blockchain/solana/SKILL.md
@@ -52,14 +52,14 @@ Override: export SOLANA_RPC_URL=https://your-private-rpc.com
 Helper script path: ~/.hermes/skills/blockchain/solana/scripts/solana_client.py
 
 ```
-python3 solana_client.py wallet   <address> [--limit N] [--all] [--no-prices]
-python3 solana_client.py tx       <signature>
-python3 solana_client.py token    <mint_address>
-python3 solana_client.py activity <address> [--limit N]
-python3 solana_client.py nft      <address>
-python3 solana_client.py whales   [--min-sol N]
-python3 solana_client.py stats
-python3 solana_client.py price    <mint_or_symbol>
+python solana_client.py wallet   <address> [--limit N] [--all] [--no-prices]
+python solana_client.py tx       <signature>
+python solana_client.py token    <mint_address>
+python solana_client.py activity <address> [--limit N]
+python solana_client.py nft      <address>
+python solana_client.py whales   [--min-sol N]
+python solana_client.py stats
+python solana_client.py price    <mint_or_symbol>
 ```
 
 ---
@@ -69,13 +69,13 @@ python3 solana_client.py price    <mint_or_symbol>
 ### 0. Setup Check
 
 ```bash
-python3 --version
+python --version
 
 # Optional: set a private RPC for better rate limits
 export SOLANA_RPC_URL="https://api.mainnet-beta.solana.com"
 
 # Confirm connectivity
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py stats
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py stats
 ```
 
 ### 1. Wallet Portfolio
@@ -85,7 +85,7 @@ portfolio total. Tokens sorted by value, dust filtered, known tokens
 labeled by name (BONK, JUP, USDC, etc.).
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
   wallet 9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM
 ```
 
@@ -103,7 +103,7 @@ Inspect a full transaction by its base58 signature. Shows balance changes
 in both SOL and USD.
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
   tx 5j7s8K...your_signature_here
 ```
 
@@ -116,7 +116,7 @@ Get SPL token metadata, current price, market cap, supply, decimals,
 mint/freeze authorities, and top 5 holders.
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
   token DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263
 ```
 
@@ -128,7 +128,7 @@ holders with percentages.
 List recent transactions for an address (default: last 10, max: 25).
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
   activity 9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM --limit 25
 ```
 
@@ -137,7 +137,7 @@ python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
 List NFTs owned by a wallet (heuristic: SPL tokens with amount=1, decimals=0).
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
   nft 9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM
 ```
 
@@ -148,7 +148,7 @@ Note: Compressed NFTs (cNFTs) are not detected by this heuristic.
 Scan the most recent block for large SOL transfers with USD values.
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py \
   whales --min-sol 500
 ```
 
@@ -160,7 +160,7 @@ Live Solana network health: current slot, epoch, TPS, supply, validator
 version, SOL price, and market cap.
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py stats
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py stats
 ```
 
 ### 8. Price Lookup
@@ -168,10 +168,10 @@ python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py stats
 Quick price check for any token by mint address or known symbol.
 
 ```bash
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price BONK
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price JUP
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price SOL
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price BONK
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price JUP
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price SOL
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py price DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263
 ```
 
 Known symbols: SOL, USDC, USDT, BONK, JUP, WETH, JTO, mSOL, stSOL,
@@ -204,5 +204,5 @@ PYTH, HNT, RNDR, WEN, W, TNSR, DRIFT, bSOL, JLP, WIF, MEW, BOME, PENGU.
 
 ```bash
 # Should print current Solana slot, TPS, and SOL price
-python3 ~/.hermes/skills/blockchain/solana/scripts/solana_client.py stats
+python ~/.hermes/skills/blockchain/solana/scripts/solana_client.py stats
 ```
diff --git a/optional-skills/creative/concept-diagrams/SKILL.md b/optional-skills/creative/concept-diagrams/SKILL.md
index 75ff2efe78f8e..d5bd15872d4fc 100644
--- a/optional-skills/creative/concept-diagrams/SKILL.md
+++ b/optional-skills/creative/concept-diagrams/SKILL.md
@@ -300,7 +300,7 @@ mkdir -p .diagrams/sn2-mechanism
 # ...write .diagrams/sn2-mechanism/index.html...
 
 # Serve on loopback only, free port
-cd .diagrams && python3 -c "
+cd .diagrams && python -c "
 import http.server, socketserver
 with socketserver.TCPServer(('127.0.0.1', 0), http.server.SimpleHTTPRequestHandler) as s:
     print(f'Serving at http://127.0.0.1:{s.server_address[1]}/')
diff --git a/optional-skills/creative/tldraw-offline/SKILL.md b/optional-skills/creative/tldraw-offline/SKILL.md
index 1c03cf729ee09..0f2af951aa5cd 100644
--- a/optional-skills/creative/tldraw-offline/SKILL.md
+++ b/optional-skills/creative/tldraw-offline/SKILL.md
@@ -64,11 +64,11 @@ is a live edit, not saved script:
 
 ```bash
 BASE=http://localhost:7236
-TOKEN=$(python3 -c "import json;print(json.load(open('$HOME/.config/tldraw/server.json'))['token'])")
+TOKEN=$(python -c "import json;print(json.load(open('$HOME/.config/tldraw/server.json'))['token'])")
 # find the focused document id
 DOC=$(curl -s "$BASE/api/search" -X POST -H 'content-type: application/json' \
   -H "Authorization: Bearer $TOKEN" \
-  -d '{"code":"return (await api.getFocusedDoc()).id"}' | python3 -c "import sys,json;print(json.load(sys.stdin)['result'])")
+  -d '{"code":"return (await api.getFocusedDoc()).id"}' | python -c "import sys,json;print(json.load(sys.stdin)['result'])")
 # run code with the live `editor` + `helpers` in scope
 curl -s "$BASE/api/doc/$DOC/exec" -X POST -H 'content-type: application/json' \
   -H "Authorization: Bearer $TOKEN" \
diff --git a/optional-skills/data-science/jupyter-notebook/SKILL.md b/optional-skills/data-science/jupyter-notebook/SKILL.md
index 17d10c1232b35..de1d71493aa3c 100644
--- a/optional-skills/data-science/jupyter-notebook/SKILL.md
+++ b/optional-skills/data-science/jupyter-notebook/SKILL.md
@@ -72,7 +72,7 @@ session via the Jupyter REST API:
 ```
 curl -s -X POST http://127.0.0.1:8888/api/sessions \
   -H "Content-Type: application/json" \
-  -d '{"path":"scratch.ipynb","type":"notebook","name":"scratch.ipynb","kernel":{"name":"python3"}}'
+  -d '{"path":"scratch.ipynb","type":"notebook","name":"scratch.ipynb","kernel":{"name":"python"}}'
 ```
 
 ## Core Workflow
diff --git a/optional-skills/devops/pinggy-tunnel/SKILL.md b/optional-skills/devops/pinggy-tunnel/SKILL.md
index d3f827a5a18c6..17051e892c1e0 100644
--- a/optional-skills/devops/pinggy-tunnel/SKILL.md
+++ b/optional-skills/devops/pinggy-tunnel/SKILL.md
@@ -79,7 +79,7 @@ curl -sI http://127.0.0.1:8000/ | head -1
 # expect HTTP/1.x 200 (or any non-connection-refused response)
 ```
 
-If nothing is listening yet, start it first (e.g. `python3 -m http.server 8000 --bind 127.0.0.1`). Pinggy will happily return a URL pointed at nothing — the user will see 502 until the origin comes up.
+If nothing is listening yet, start it first (e.g. `python -m http.server 8000 --bind 127.0.0.1`). Pinggy will happily return a URL pointed at nothing — the user will see 502 until the origin comes up.
 
 ### 2. Launch the tunnel as a background process
 
@@ -203,7 +203,7 @@ class H(http.server.BaseHTTPRequestHandler):
     def log_message(self,*a,**k): pass
 http.server.HTTPServer(("127.0.0.1", 18080), H).serve_forever()
 PY
-nohup python3 /tmp/webhook-server.py >/tmp/webhook-server.log 2>&1 &
+nohup python /tmp/webhook-server.py >/tmp/webhook-server.log 2>&1 &
 echo $! >/tmp/webhook-server.pid
 
 # 2. Tunnel — bearer-token-gate so randos can't pollute the capture log
@@ -228,7 +228,7 @@ Use when a remote MCP client (Claude Desktop on another machine, a teammate's ed
 
 ```bash
 # 1. Start the MCP server in HTTP mode (example: a FastMCP server on port 8765)
-nohup python3 my_mcp_server.py --transport http --port 8765 \
+nohup python my_mcp_server.py --transport http --port 8765 \
     >/tmp/mcp-server.log 2>&1 &
 echo $! >/tmp/mcp-server.pid
 
@@ -289,7 +289,7 @@ ssh -p 443 -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null \
 
 ```bash
 # End-to-end: spin up a trivial origin, tunnel it, hit it, tear down
-python3 -m http.server 18000 --bind 127.0.0.1 >/tmp/origin.log 2>&1 &
+python -m http.server 18000 --bind 127.0.0.1 >/tmp/origin.log 2>&1 &
 ORIGIN_PID=$!
 
 nohup ssh -p 443 \
diff --git a/optional-skills/finance/stocks/SKILL.md b/optional-skills/finance/stocks/SKILL.md
index 347b0c5972c11..37ecec00cc208 100644
--- a/optional-skills/finance/stocks/SKILL.md
+++ b/optional-skills/finance/stocks/SKILL.md
@@ -38,7 +38,7 @@ Invoke through the `terminal` tool. Once installed:
 
 ```
 SCRIPT=~/.hermes/skills/finance/stocks/scripts/stocks_client.py
-python3 $SCRIPT quote AAPL
+python $SCRIPT quote AAPL
 ```
 
 All output is JSON on stdout — pipe through `jq` if you want to slice it.
@@ -46,12 +46,12 @@ All output is JSON on stdout — pipe through `jq` if you want to slice it.
 ## Quick Reference
 
 ```
-python3 $SCRIPT quote AAPL
-python3 $SCRIPT quote AAPL MSFT GOOGL TSLA
-python3 $SCRIPT search "Tesla"
-python3 $SCRIPT history NVDA --range 6mo
-python3 $SCRIPT compare AAPL MSFT GOOGL
-python3 $SCRIPT crypto BTC ETH SOL
+python $SCRIPT quote AAPL
+python $SCRIPT quote AAPL MSFT GOOGL TSLA
+python $SCRIPT search "Tesla"
+python $SCRIPT history NVDA --range 6mo
+python $SCRIPT compare AAPL MSFT GOOGL
+python $SCRIPT crypto BTC ETH SOL
 ```
 
 ## Commands
@@ -89,7 +89,7 @@ Crypto prices. Pass `BTC` (the script appends `-USD` automatically).
 ## Verification
 
 ```
-python3 ~/.hermes/skills/finance/stocks/scripts/stocks_client.py quote AAPL
+python ~/.hermes/skills/finance/stocks/scripts/stocks_client.py quote AAPL
 ```
 
 Returns a JSON object with `symbol: "AAPL"` and a numeric `price` field.
diff --git a/optional-skills/gaming/pokemon-player/SKILL.md b/optional-skills/gaming/pokemon-player/SKILL.md
index 6da6584e34909..439f6b159f8b8 100644
--- a/optional-skills/gaming/pokemon-player/SKILL.md
+++ b/optional-skills/gaming/pokemon-player/SKILL.md
@@ -23,7 +23,7 @@ Play Pokemon games via headless emulation using the `pokemon-agent` package.
 The repo is NousResearch/pokemon-agent on GitHub. Clone it, then
 set up a Python 3.10+ virtual environment. Use uv (preferred for speed)
 to create the venv and install the package in editable mode with the
-pyboy extra. If uv is not available, fall back to python3 -m venv + pip.
+pyboy extra. If uv is not available, fall back to python -m venv + pip.
 
 If a checkout already exists (e.g. ~/pokemon-agent with a venv ready),
 just cd there and source .venv/bin/activate instead of recloning.
diff --git a/optional-skills/health/fitness-nutrition/SKILL.md b/optional-skills/health/fitness-nutrition/SKILL.md
index 561a44d5e8c37..f0024c45cd4c2 100644
--- a/optional-skills/health/fitness-nutrition/SKILL.md
+++ b/optional-skills/health/fitness-nutrition/SKILL.md
@@ -12,7 +12,7 @@ metadata:
     tags: [health, fitness, nutrition, gym, workout, diet, exercise]
     category: health
     prerequisites:
-      commands: [curl, python3]
+      commands: [curl, python]
 required_environment_variables:
   - name: USDA_API_KEY
     prompt: "USDA FoodData Central API key (free)"
@@ -110,9 +110,9 @@ Equipment:
 ```bash
 # Search exercises by name
 QUERY="$1"
-ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$QUERY")
+ENCODED=$(python -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$QUERY")
 curl -s "https://wger.de/api/v2/exercise/search/?term=${ENCODED}&language=english&format=json" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 for s in data.get('suggestions',[])[:10]:
@@ -125,7 +125,7 @@ for s in data.get('suggestions',[])[:10]:
 # Get full details for a specific exercise
 EXERCISE_ID="$1"
 curl -s "https://wger.de/api/v2/exerciseinfo/${EXERCISE_ID}/?format=json" \
-  | python3 -c "
+  | python -c "
 import json,sys,html,re
 data=json.load(sys.stdin)
 trans=[t for t in data.get('translations',[]) if t.get('language')==2]
@@ -147,7 +147,7 @@ if imgs: print(f\"Image     : {imgs[0].get('image','')}\")
 # Combine filters as needed: ?muscles=4&equipment=1&language=2&status=2
 FILTER="$1"  # e.g. "muscles=4" or "category=11" or "equipment=3"
 curl -s "https://wger.de/api/v2/exercise/?${FILTER}&language=2&status=2&limit=20&format=json" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 print(f'Found {data.get(\"count\",0)} exercises.')
@@ -165,9 +165,9 @@ DEMO_KEY = 30 requests/hour. Free signup key = 1,000 requests/hour.
 # Search foods by name
 FOOD="$1"
 API_KEY="${USDA_API_KEY:-DEMO_KEY}"
-ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$FOOD")
+ENCODED=$(python -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$FOOD")
 curl -s "https://api.nal.usda.gov/fdc/v1/foods/search?api_key=${API_KEY}&query=${ENCODED}&pageSize=5&dataType=Foundation,SR%20Legacy" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 foods=data.get('foods',[])
@@ -188,7 +188,7 @@ for f in foods:
 FDC_ID="$1"
 API_KEY="${USDA_API_KEY:-DEMO_KEY}"
 curl -s "https://api.nal.usda.gov/fdc/v1/food/${FDC_ID}?api_key=${API_KEY}" \
-  | python3 -c "
+  | python -c "
 import json,sys
 d=json.load(sys.stdin)
 print(f\"Food: {d.get('description','N/A')}\")
@@ -206,11 +206,11 @@ for x in sorted(d.get('foodNutrients',[]),key=lambda x:x.get('nutrient',{}).get(
 Use the helper scripts in `scripts/` for batch operations,
 or run inline for single calculations:
 
-- `python3 scripts/body_calc.py bmi <weight_kg> <height_cm>`
-- `python3 scripts/body_calc.py tdee <weight_kg> <height_cm> <age> <M|F> <activity 1-5>`
-- `python3 scripts/body_calc.py 1rm <weight> <reps>`
-- `python3 scripts/body_calc.py macros <tdee_kcal> <cut|maintain|bulk>`
-- `python3 scripts/body_calc.py bodyfat <M|F> <neck_cm> <waist_cm> [hip_cm] <height_cm>`
+- `python scripts/body_calc.py bmi <weight_kg> <height_cm>`
+- `python scripts/body_calc.py tdee <weight_kg> <height_cm> <age> <M|F> <activity 1-5>`
+- `python scripts/body_calc.py 1rm <weight> <reps>`
+- `python scripts/body_calc.py macros <tdee_kcal> <cut|maintain|bulk>`
+- `python scripts/body_calc.py bodyfat <M|F> <neck_cm> <waist_cm> [hip_cm] <height_cm>`
 
 See `references/FORMULAS.md` for the science behind each formula.
 
@@ -249,4 +249,4 @@ After calculators: sanity-check outputs (e.g. TDEE should be 1500-3500 for most
 | List muscles | wger | `GET /api/v2/muscle/` |
 | Search foods | USDA | `GET /fdc/v1/foods/search?query=&dataType=Foundation,SR Legacy` |
 | Food details | USDA | `GET /fdc/v1/food/{fdcId}` |
-| BMI / TDEE / 1RM / macros | offline | `python3 scripts/body_calc.py` |
\ No newline at end of file
+| BMI / TDEE / 1RM / macros | offline | `python scripts/body_calc.py` |
\ No newline at end of file
diff --git a/optional-skills/mcp/fastmcp/SKILL.md b/optional-skills/mcp/fastmcp/SKILL.md
index 3d54e8d997085..53fe30407fbd0 100644
--- a/optional-skills/mcp/fastmcp/SKILL.md
+++ b/optional-skills/mcp/fastmcp/SKILL.md
@@ -11,7 +11,7 @@ metadata:
     homepage: https://gofastmcp.com
     related_skills: [hermes-agent, mcporter]
 prerequisites:
-  commands: [python3]
+  commands: [python]
 ---
 
 # FastMCP
diff --git a/optional-skills/migration/openclaw-migration/SKILL.md b/optional-skills/migration/openclaw-migration/SKILL.md
index 4a04fb46cae2c..500a49a50bb94 100644
--- a/optional-skills/migration/openclaw-migration/SKILL.md
+++ b/optional-skills/migration/openclaw-migration/SKILL.md
@@ -229,37 +229,37 @@ The helper script still supports category-level `--include` / `--exclude`, but t
 Dry run with full discovery:
 
 ```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py
+python ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py
 ```
 
 When using the terminal tool, prefer an absolute invocation pattern such as:
 
 ```json
-{"command":"python3 /home/USER/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py","workdir":"/home/USER"}
+{"command":"python /home/USER/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py","workdir":"/home/USER"}
 ```
 
 Dry run with the user-data preset:
 
 ```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --preset user-data
+python ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --preset user-data
 ```
 
 Execute a user-data migration:
 
 ```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict skip
+python ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict skip
 ```
 
 Execute a full compatible migration:
 
 ```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset full --migrate-secrets --skill-conflict skip
+python ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset full --migrate-secrets --skill-conflict skip
 ```
 
 Execute with workspace instructions included:
 
 ```bash
-python3 ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict rename --workspace-target "/absolute/workspace/path"
+python ~/.hermes/skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py --execute --preset user-data --skill-conflict rename --workspace-target "/absolute/workspace/path"
 ```
 
 Do not use `$PWD` or the home directory as the workspace target by default. Ask for an explicit workspace path first.
diff --git a/optional-skills/productivity/telephony/SKILL.md b/optional-skills/productivity/telephony/SKILL.md
index 23d4a6b593fe1..0e8a8d2fdf143 100644
--- a/optional-skills/productivity/telephony/SKILL.md
+++ b/optional-skills/productivity/telephony/SKILL.md
@@ -154,33 +154,33 @@ Sign up at:
 Then save credentials into Hermes:
 
 ```bash
-python3 "$SCRIPT" save-twilio ACXXXXXXXXXXXXXXXXXXXXXXXXXXXX your_auth_token_here
+python "$SCRIPT" save-twilio ACXXXXXXXXXXXXXXXXXXXXXXXXXXXX your_auth_token_here
 ```
 
 Search for available numbers:
 
 ```bash
-python3 "$SCRIPT" twilio-search --country US --area-code 702 --limit 5
+python "$SCRIPT" twilio-search --country US --area-code 702 --limit 5
 ```
 
 Buy and remember a number:
 
 ```bash
-python3 "$SCRIPT" twilio-buy "+17025551234" --save-env
+python "$SCRIPT" twilio-buy "+17025551234" --save-env
 ```
 
 List owned numbers:
 
 ```bash
-python3 "$SCRIPT" twilio-owned
+python "$SCRIPT" twilio-owned
 ```
 
 Set one of them as the default later:
 
 ```bash
-python3 "$SCRIPT" twilio-set-default "+17025551234" --save-env
+python "$SCRIPT" twilio-set-default "+17025551234" --save-env
 # or
-python3 "$SCRIPT" twilio-set-default PNXXXXXXXXXXXXXXXXXXXXXXXXXXXX --save-env
+python "$SCRIPT" twilio-set-default PNXXXXXXXXXXXXXXXXXXXXXXXXXXXX --save-env
 ```
 
 ### Bland.ai — easiest outbound AI calling
@@ -191,7 +191,7 @@ Sign up at:
 Save config:
 
 ```bash
-python3 "$SCRIPT" save-bland your_bland_api_key --voice mason
+python "$SCRIPT" save-bland your_bland_api_key --voice mason
 ```
 
 ### Vapi — better conversational voice quality
@@ -202,19 +202,19 @@ Sign up at:
 Save the API key first:
 
 ```bash
-python3 "$SCRIPT" save-vapi your_vapi_api_key
+python "$SCRIPT" save-vapi your_vapi_api_key
 ```
 
 Import your owned Twilio number into Vapi and persist the returned phone number ID:
 
 ```bash
-python3 "$SCRIPT" vapi-import-twilio --save-env
+python "$SCRIPT" vapi-import-twilio --save-env
 ```
 
 If you already know the Vapi phone number ID, save it directly:
 
 ```bash
-python3 "$SCRIPT" save-vapi your_vapi_api_key --phone-number-id vapi_phone_number_id_here
+python "$SCRIPT" save-vapi your_vapi_api_key --phone-number-id vapi_phone_number_id_here
 ```
 
 ## Diagnose current state
@@ -222,7 +222,7 @@ python3 "$SCRIPT" save-vapi your_vapi_api_key --phone-number-id vapi_phone_numbe
 At any time, inspect what the skill already knows:
 
 ```bash
-python3 "$SCRIPT" diagnose
+python "$SCRIPT" diagnose
 ```
 
 Use this first when resuming work in a later session.
@@ -233,35 +233,35 @@ Use this first when resuming work in a later session.
 
 1. Save Twilio credentials:
 ```bash
-python3 "$SCRIPT" save-twilio AC... auth_token_here
+python "$SCRIPT" save-twilio AC... auth_token_here
 ```
 
 2. Search for a number:
 ```bash
-python3 "$SCRIPT" twilio-search --country US --area-code 702 --limit 10
+python "$SCRIPT" twilio-search --country US --area-code 702 --limit 10
 ```
 
 3. Buy it and save it into `${HERMES_HOME:-~/.hermes}/.env` + state:
 ```bash
-python3 "$SCRIPT" twilio-buy "+17025551234" --save-env
+python "$SCRIPT" twilio-buy "+17025551234" --save-env
 ```
 
 4. Next session, run:
 ```bash
-python3 "$SCRIPT" diagnose
+python "$SCRIPT" diagnose
 ```
 This shows the remembered default number and inbox checkpoint state.
 
 ### B. Send a text from the agent number
 
 ```bash
-python3 "$SCRIPT" twilio-send-sms "+15551230000" "Your deployment completed successfully."
+python "$SCRIPT" twilio-send-sms "+15551230000" "Your deployment completed successfully."
 ```
 
 With media:
 
 ```bash
-python3 "$SCRIPT" twilio-send-sms "+15551230000" "Here is the chart." --media-url "https://example.com/chart.png"
+python "$SCRIPT" twilio-send-sms "+15551230000" "Here is the chart." --media-url "https://example.com/chart.png"
 ```
 
 ### C. Check inbound texts later with no webhook server
@@ -269,13 +269,13 @@ python3 "$SCRIPT" twilio-send-sms "+15551230000" "Here is the chart." --media-ur
 Poll the inbox for the default Twilio number:
 
 ```bash
-python3 "$SCRIPT" twilio-inbox --limit 20
+python "$SCRIPT" twilio-inbox --limit 20
 ```
 
 Only show messages that arrived after the last checkpoint, and advance the checkpoint when you're done reading:
 
 ```bash
-python3 "$SCRIPT" twilio-inbox --since-last --mark-seen
+python "$SCRIPT" twilio-inbox --since-last --mark-seen
 ```
 
 This is the main answer to “how do I access messages the number receives next time the skill is loaded?”
@@ -283,7 +283,7 @@ This is the main answer to “how do I access messages the number receives next
 ### D. Make a direct Twilio call with built-in TTS
 
 ```bash
-python3 "$SCRIPT" twilio-call "+15551230000" --message "Hello! This is Hermes calling with your status update." --voice Polly.Joanna
+python "$SCRIPT" twilio-call "+15551230000" --message "Hello! This is Hermes calling with your status update." --voice Polly.Joanna
 ```
 
 ### E. Call with a prerecorded / custom voice message
@@ -298,7 +298,7 @@ Use this when:
 Generate or host audio separately, then:
 
 ```bash
-python3 "$SCRIPT" twilio-call "+155****0000" --audio-url "https://example.com/briefing.mp3"
+python "$SCRIPT" twilio-call "+155****0000" --audio-url "https://example.com/briefing.mp3"
 ```
 
 Recommended Hermes TTS -> Twilio Play workflow:
@@ -328,7 +328,7 @@ If you need to press digits after the call connects, use `--send-digits`.
 Twilio interprets `w` as a short wait.
 
 ```bash
-python3 "$SCRIPT" twilio-call "+18005551234" --message "Connecting to billing now." --send-digits "ww1w2w3"
+python "$SCRIPT" twilio-call "+18005551234" --message "Connecting to billing now." --send-digits "ww1w2w3"
 ```
 
 This is useful for reaching a specific menu branch before handing off to a human or delivering a short status message.
@@ -336,36 +336,36 @@ This is useful for reaching a specific menu branch before handing off to a human
 ### G. Outbound AI phone call with Bland.ai
 
 ```bash
-python3 "$SCRIPT" ai-call "+15551230000" "Call the dental office, ask for a cleaning appointment on Tuesday afternoon, and if they do not have Tuesday availability, ask for Wednesday or Thursday instead." --provider bland --voice mason --max-duration 3
+python "$SCRIPT" ai-call "+15551230000" "Call the dental office, ask for a cleaning appointment on Tuesday afternoon, and if they do not have Tuesday availability, ask for Wednesday or Thursday instead." --provider bland --voice mason --max-duration 3
 ```
 
 Check status:
 
 ```bash
-python3 "$SCRIPT" ai-status <call_id> --provider bland
+python "$SCRIPT" ai-status <call_id> --provider bland
 ```
 
 Ask Bland analysis questions after completion:
 
 ```bash
-python3 "$SCRIPT" ai-status <call_id> --provider bland --analyze "Was the appointment confirmed?,What date and time?,Any special instructions?"
+python "$SCRIPT" ai-status <call_id> --provider bland --analyze "Was the appointment confirmed?,What date and time?,Any special instructions?"
 ```
 
 ### H. Outbound AI phone call with Vapi on your owned number
 
 1. Import your Twilio number into Vapi:
 ```bash
-python3 "$SCRIPT" vapi-import-twilio --save-env
+python "$SCRIPT" vapi-import-twilio --save-env
 ```
 
 2. Place the call:
 ```bash
-python3 "$SCRIPT" ai-call "+15551230000" "You are calling to make a dinner reservation for two at 7:30 PM. If that is unavailable, ask for the nearest time between 6:30 and 8:30 PM." --provider vapi --max-duration 4
+python "$SCRIPT" ai-call "+15551230000" "You are calling to make a dinner reservation for two at 7:30 PM. If that is unavailable, ask for the nearest time between 6:30 and 8:30 PM." --provider vapi --max-duration 4
 ```
 
 3. Check result:
 ```bash
-python3 "$SCRIPT" ai-status <call_id> --provider vapi
+python "$SCRIPT" ai-status <call_id> --provider vapi
 ```
 
 ## Suggested agent procedure
diff --git a/optional-skills/research/domain-intel/SKILL.md b/optional-skills/research/domain-intel/SKILL.md
index 8d939b6487311..1b38e71ffe3b3 100644
--- a/optional-skills/research/domain-intel/SKILL.md
+++ b/optional-skills/research/domain-intel/SKILL.md
@@ -22,23 +22,23 @@ This skill includes `scripts/domain_intel.py` — a complete CLI tool for all do
 
 ```bash
 # Subdomain discovery via Certificate Transparency logs
-python3 SKILL_DIR/scripts/domain_intel.py subdomains example.com
+python SKILL_DIR/scripts/domain_intel.py subdomains example.com
 
 # SSL certificate inspection (expiry, cipher, SANs, issuer)
-python3 SKILL_DIR/scripts/domain_intel.py ssl example.com
+python SKILL_DIR/scripts/domain_intel.py ssl example.com
 
 # WHOIS lookup (registrar, dates, name servers — 100+ TLDs)
-python3 SKILL_DIR/scripts/domain_intel.py whois example.com
+python SKILL_DIR/scripts/domain_intel.py whois example.com
 
 # DNS records (A, AAAA, MX, NS, TXT, CNAME)
-python3 SKILL_DIR/scripts/domain_intel.py dns example.com
+python SKILL_DIR/scripts/domain_intel.py dns example.com
 
 # Domain availability check (passive: DNS + WHOIS + SSL signals)
-python3 SKILL_DIR/scripts/domain_intel.py available coolstartup.io
+python SKILL_DIR/scripts/domain_intel.py available coolstartup.io
 
 # Bulk analysis — multiple domains, multiple checks in parallel
-python3 SKILL_DIR/scripts/domain_intel.py bulk example.com github.com google.com
-python3 SKILL_DIR/scripts/domain_intel.py bulk example.com github.com --checks ssl,dns
+python SKILL_DIR/scripts/domain_intel.py bulk example.com github.com google.com
+python SKILL_DIR/scripts/domain_intel.py bulk example.com github.com --checks ssl,dns
 ```
 
 `SKILL_DIR` is the directory containing this SKILL.md file. All output is structured JSON.
diff --git a/optional-skills/research/drug-discovery/SKILL.md b/optional-skills/research/drug-discovery/SKILL.md
index 64db7e91ecf21..63a9c5376ce9b 100644
--- a/optional-skills/research/drug-discovery/SKILL.md
+++ b/optional-skills/research/drug-discovery/SKILL.md
@@ -9,7 +9,7 @@ metadata:
   hermes:
     tags: [science, chemistry, pharmacology, research, health]
 prerequisites:
-  commands: [curl, python3]
+  commands: [curl, python]
 ---
 
 # Drug Discovery & Pharmaceutical Research
@@ -28,9 +28,9 @@ by target, activity, or molecule name. No API key required.
 ```bash
 # Search compounds by target name (e.g. "EGFR", "COX-2", "ACE")
 TARGET="$1"
-ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$TARGET")
+ENCODED=$(python -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$TARGET")
 curl -s "https://www.ebi.ac.uk/chembl/api/data/target/search?q=${ENCODED}&format=json" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 targets=data.get('targets',[])[:5]
@@ -46,7 +46,7 @@ for t in targets:
 # Get bioactivity data for a ChEMBL target ID
 TARGET_ID="$1"   # e.g. CHEMBL203
 curl -s "https://www.ebi.ac.uk/chembl/api/data/activity?target_chembl_id=${TARGET_ID}&pchembl_value__gte=6&limit=10&format=json" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 acts=data.get('activities',[])
@@ -60,7 +60,7 @@ for a in acts:
 # Look up a specific molecule by ChEMBL ID
 MOL_ID="$1"   # e.g. CHEMBL25 (aspirin)
 curl -s "https://www.ebi.ac.uk/chembl/api/data/molecule/${MOL_ID}?format=json" \
-  | python3 -c "
+  | python -c "
 import json,sys
 m=json.load(sys.stdin)
 props=m.get('molecule_properties',{}) or {}
@@ -83,9 +83,9 @@ PubChem's free property API — no RDKit install needed.
 
 ```bash
 COMPOUND="$1"
-ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$COMPOUND")
+ENCODED=$(python -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$COMPOUND")
 curl -s "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/${ENCODED}/property/MolecularWeight,XLogP,HBondDonorCount,HBondAcceptorCount,RotatableBondCount,TPSA,InChIKey/JSON" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 props=data['PropertyTable']['Properties'][0]
@@ -114,9 +114,9 @@ print(f'  Both rules met: {\"Yes → good oral absorption predicted\" if tpsa<=1
 
 ```bash
 DRUG="$1"
-ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$DRUG")
+ENCODED=$(python -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$DRUG")
 curl -s "https://api.fda.gov/drug/label.json?search=drug_interactions:\"${ENCODED}\"&limit=3" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 results=data.get('results',[])
@@ -135,9 +135,9 @@ for r in results[:2]:
 
 ```bash
 DRUG="$1"
-ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$DRUG")
+ENCODED=$(python -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$DRUG")
 curl -s "https://api.fda.gov/drug/event.json?search=patient.drug.medicinalproduct:\"${ENCODED}\"&count=patient.reaction.reactionmeddrapt.exact&limit=10" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 results=data.get('results',[])
@@ -154,11 +154,11 @@ for r in results[:10]:
 
 ```bash
 COMPOUND="$1"
-ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$COMPOUND")
+ENCODED=$(python -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$COMPOUND")
 CID=$(curl -s "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/${ENCODED}/cids/TXT" | head -1 | tr -d '[:space:]')
 echo "PubChem CID: $CID"
 curl -s "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/${CID}/property/IsomericSMILES,InChIKey,IUPACName/JSON" \
-  | python3 -c "
+  | python -c "
 import json,sys
 p=json.load(sys.stdin)['PropertyTable']['Properties'][0]
 print(f\"IUPAC Name : {p.get('IUPACName','N/A')}\")
@@ -174,7 +174,7 @@ GENE="$1"
 curl -s -X POST "https://api.platform.opentargets.org/api/v4/graphql" \
   -H "Content-Type: application/json" \
   -d "{\"query\":\"{ search(queryString: \\\"${GENE}\\\", entityNames: [\\\"target\\\"], page: {index: 0, size: 1}) { hits { id score object { ... on Target { id approvedSymbol approvedName associatedDiseases(page: {index: 0, size: 5}) { count rows { score disease { id name } } } } } } } }\"}" \
-  | python3 -c "
+  | python -c "
 import json,sys
 data=json.load(sys.stdin)
 hits=data.get('data',{}).get('search',{}).get('hits',[])
diff --git a/optional-skills/research/osint-investigation/SKILL.md b/optional-skills/research/osint-investigation/SKILL.md
index 0e35da9f8503c..7513a020ee859 100644
--- a/optional-skills/research/osint-investigation/SKILL.md
+++ b/optional-skills/research/osint-investigation/SKILL.md
@@ -100,24 +100,24 @@ Each source has a stdlib-only fetch script in `SKILL_DIR/scripts/`:
 
 ```bash
 # SEC EDGAR filings (corporate disclosures)
-python3 SKILL_DIR/scripts/fetch_sec_edgar.py --cik 0000320193 \
+python SKILL_DIR/scripts/fetch_sec_edgar.py --cik 0000320193 \
     --types 10-K,10-Q --out data/edgar_filings.csv
 
 # USAspending federal contracts
-python3 SKILL_DIR/scripts/fetch_usaspending.py --recipient "EXAMPLE CORP" \
+python SKILL_DIR/scripts/fetch_usaspending.py --recipient "EXAMPLE CORP" \
     --fy 2024 --out data/contracts.csv
 
 # Senate LD-1 / LD-2 lobbying disclosures
-python3 SKILL_DIR/scripts/fetch_senate_ld.py --client "EXAMPLE CORP" \
+python SKILL_DIR/scripts/fetch_senate_ld.py --client "EXAMPLE CORP" \
     --year 2024 --out data/lobbying.csv
 
 # OFAC SDN sanctions list (full snapshot)
-python3 SKILL_DIR/scripts/fetch_ofac_sdn.py --out data/ofac_sdn.csv
+python SKILL_DIR/scripts/fetch_ofac_sdn.py --out data/ofac_sdn.csv
 
 # ICIJ Offshore Leaks — downloads ~70 MB bulk CSV on first use,
 # then searches it locally. Cached for 30 days under
 # $HERMES_OSINT_CACHE/icij/ (default: ~/.cache/hermes-osint/icij/).
-python3 SKILL_DIR/scripts/fetch_icij_offshore.py --entity "EXAMPLE CORP" \
+python SKILL_DIR/scripts/fetch_icij_offshore.py --entity "EXAMPLE CORP" \
     --out data/icij.csv
 ```
 
@@ -125,31 +125,31 @@ python3 SKILL_DIR/scripts/fetch_icij_offshore.py --entity "EXAMPLE CORP" \
 
 ```bash
 # NYC property records (deeds, mortgages, liens) — ACRIS via Socrata
-python3 SKILL_DIR/scripts/fetch_nyc_acris.py --name "SMITH, JOHN" \
+python SKILL_DIR/scripts/fetch_nyc_acris.py --name "SMITH, JOHN" \
     --out data/acris.csv
-python3 SKILL_DIR/scripts/fetch_nyc_acris.py --address "571 HUDSON" \
+python SKILL_DIR/scripts/fetch_nyc_acris.py --address "571 HUDSON" \
     --out data/acris_addr.csv
 
 # OpenCorporates — 130+ jurisdiction corporate registry
 # (free token required; set OPENCORPORATES_API_TOKEN or pass --token)
-python3 SKILL_DIR/scripts/fetch_opencorporates.py --query "Example Corp" \
+python SKILL_DIR/scripts/fetch_opencorporates.py --query "Example Corp" \
     --jurisdiction us_ny --out data/opencorporates.csv
 
 # CourtListener — federal + state court opinions, PACER dockets
-python3 SKILL_DIR/scripts/fetch_courtlistener.py --query "Smith v. Example Corp" \
+python SKILL_DIR/scripts/fetch_courtlistener.py --query "Smith v. Example Corp" \
     --type opinions --out data/courts.csv
 
 # Wayback Machine — historical web captures
-python3 SKILL_DIR/scripts/fetch_wayback.py --url "example.com" \
+python SKILL_DIR/scripts/fetch_wayback.py --url "example.com" \
     --match host --collapse digest --out data/wayback.csv
 
 # Wikipedia + Wikidata — narrative bio + structured facts
 # Set HERMES_OSINT_UA=your-app/1.0 (your@email) to identify yourself
-python3 SKILL_DIR/scripts/fetch_wikipedia.py --query "Bill Gates" \
+python SKILL_DIR/scripts/fetch_wikipedia.py --query "Bill Gates" \
     --out data/wp.csv
 
 # GDELT — global news in 100+ languages, ~2015→present
-python3 SKILL_DIR/scripts/fetch_gdelt.py --query '"Example Corp"' \
+python SKILL_DIR/scripts/fetch_gdelt.py --query '"Example Corp"' \
     --timespan 1y --out data/gdelt.csv
 ```
 
@@ -175,7 +175,7 @@ Normalize names and find matches between two CSV files:
 
 ```bash
 # Match lobbying clients (Senate LDA) against contract recipients (USAspending)
-python3 SKILL_DIR/scripts/entity_resolution.py \
+python SKILL_DIR/scripts/entity_resolution.py \
     --left  data/lobbying.csv   --left-name-col  client_name \
     --right data/contracts.csv  --right-name-col recipient_name \
     --out data/cross_links.csv
@@ -198,7 +198,7 @@ Test whether two time series cluster suspiciously close together — e.g.
 lobbying filings near contract awards — using a permutation test:
 
 ```bash
-python3 SKILL_DIR/scripts/timing_analysis.py \
+python SKILL_DIR/scripts/timing_analysis.py \
     --donations data/lobbying.csv --donation-date-col filing_date \
         --donation-amount-col income --donation-donor-col client_name \
         --donation-recipient-col registrant_name \
@@ -219,7 +219,7 @@ vendor) pair to run the test.
 ### 5. Build the findings JSON (evidence chain)
 
 ```bash
-python3 SKILL_DIR/scripts/build_findings.py \
+python SKILL_DIR/scripts/build_findings.py \
     --cross-links data/cross_links.csv \
     --timing data/timing.json \
     --out data/findings.json
diff --git a/optional-skills/security/godmode/SKILL.md b/optional-skills/security/godmode/SKILL.md
index deda3471785e4..e7d221465bc16 100644
--- a/optional-skills/security/godmode/SKILL.md
+++ b/optional-skills/security/godmode/SKILL.md
@@ -186,7 +186,7 @@ Use the Parseltongue script to transform trigger words before sending:
 
 ```bash
 # Quick one-liner via execute_code
-python3 scripts/parseltongue.py "How do I hack into a WiFi network?" --tier standard
+python scripts/parseltongue.py "How do I hack into a WiFi network?" --tier standard
 ```
 
 Or use `execute_code` inline:
diff --git a/optional-skills/security/oss-forensics/SKILL.md b/optional-skills/security/oss-forensics/SKILL.md
index 048cebcf8305a..6492b7348d2dc 100644
--- a/optional-skills/security/oss-forensics/SKILL.md
+++ b/optional-skills/security/oss-forensics/SKILL.md
@@ -74,7 +74,7 @@ Read these before every investigation step. Violating them invalidates the repor
    ```
 2. Initialize the evidence store:
    ```bash
-   python3 SKILL_DIR/scripts/evidence-store.py --store evidence.json list
+   python SKILL_DIR/scripts/evidence-store.py --store evidence.json list
    ```
 3. Copy the forensic report template:
    ```bash
@@ -144,7 +144,7 @@ git log --all --diff-filter=A --name-only --format="%H %ai" -- "*.so" "*.dll" "*
 git log --show-signature --format="%H %ai %aN" > ../signature_check.txt 2>&1
 ```
 
-**Evidence to collect** (add via `python3 SKILL_DIR/scripts/evidence-store.py add`):
+**Evidence to collect** (add via `python SKILL_DIR/scripts/evidence-store.py add`):
 - Each dangling commit SHA → type: `git`
 - Force-push evidence (reflog showing history rewrite) → type: `git`
 - Unsigned commits from verified contributors → type: `git`
@@ -297,7 +297,7 @@ LIMIT 200
 
 After all investigators complete:
 
-1. Run `python3 SKILL_DIR/scripts/evidence-store.py --store evidence.json list` to see all collected evidence.
+1. Run `python SKILL_DIR/scripts/evidence-store.py --store evidence.json list` to see all collected evidence.
 2. For each piece of evidence, verify the `content_sha256` hash matches the original source.
 3. Group evidence by:
    - **Timeline**: Sort all timestamped evidence chronologically
@@ -368,7 +368,7 @@ Populate `investigation-report.md` using the template in [forensic-report.md](./
 
 ## Phase 7: Completion
 
-1. Run final evidence count: `python3 SKILL_DIR/scripts/evidence-store.py --store evidence.json list`
+1. Run final evidence count: `python SKILL_DIR/scripts/evidence-store.py --store evidence.json list`
 2. Archive the full investigation directory.
 3. If compromise is confirmed:
    - List immediate mitigations (rotate credentials, pin dependency hashes, notify affected users)
diff --git a/optional-skills/security/unbroker/SKILL.md b/optional-skills/security/unbroker/SKILL.md
index 42885a501f673..5187d0b4529e9 100644
--- a/optional-skills/security/unbroker/SKILL.md
+++ b/optional-skills/security/unbroker/SKILL.md
@@ -6,7 +6,7 @@ author: SHL0MS (github.com/SHL0MS)
 license: MIT
 platforms: [linux, macos, windows]
 prerequisites:
-  commands: [python3]
+  commands: [python]
 metadata:
   hermes:
     tags: [privacy, data-broker, opt-out, ccpa, gdpr, security, doxxing]
@@ -61,7 +61,7 @@ verifying re-scan.
 
 ## Prerequisites
 
-- `python3` (stdlib only; no extra packages needed for the core engine).
+- `python` (stdlib only; no extra packages needed for the core engine).
 - **Optional upgrades** (the skill works zero-config without these; `setup --auto` turns on every
   one it detects, reading credentials from the shell env **and from `$HERMES_HOME/.env`** so keys
   Hermes already loads for its own tools are picked up without re-exporting - each one converts a
@@ -98,7 +98,7 @@ verifying re-scan.
 Run everything through the `terminal` tool. From this skill's directory:
 
 ```bash
-PDD="python3 scripts/pdd.py"
+PDD="python scripts/pdd.py"
 ```
 
 The engine stores data under `$PDD_DATA_DIR` (default `$HERMES_HOME/unbroker`), written
@@ -311,7 +311,7 @@ recording `found` and before any deletion.
 ## Verification
 
 - `scripts/run_tests.sh tests/skills/test_unbroker_skill.py` (hermetic; no network), or the
-  dependency-free runner `python3 tests/skills/test_unbroker_skill.py`.
+  dependency-free runner `python tests/skills/test_unbroker_skill.py`.
 - Dry run: `$PDD setup --auto && $PDD doctor && SID=$($PDD intake --full-name "Test Person"
-  --email t@example.com --consent | python3 -c 'import sys,json;print(json.load(sys.stdin)["subject_id"])')
+  --email t@example.com --consent | python -c 'import sys,json;print(json.load(sys.stdin)["subject_id"])')
   && $PDD next "$SID"` and confirm a readiness summary plus an ordered action queue.
diff --git a/optional-skills/software-development/ast-grep/SKILL.md b/optional-skills/software-development/ast-grep/SKILL.md
index 9383330b8c84d..581c2358572e5 100644
--- a/optional-skills/software-development/ast-grep/SKILL.md
+++ b/optional-skills/software-development/ast-grep/SKILL.md
@@ -83,7 +83,7 @@ A single-file Python 3 stdlib wrapper. Same on every OS. The agent's default ent
 ### `search` — find all matches of a pattern
 
 ```bash
-python3 scripts/ast_grep_helper.py search 'console.log($MSG)' --lang ts src/
+python scripts/ast_grep_helper.py search 'console.log($MSG)' --lang ts src/
 ```
 
 Validates the pattern offline first. If the pattern looks like regex (`\w`, `.*`, `|`, etc.) the helper exits with a hint and never calls `sg` — saves a round-trip. Pass `--force` to skip validation.
@@ -98,10 +98,10 @@ Flags:
 
 ```bash
 # Dry-run preview (default — no files mutated)
-python3 scripts/ast_grep_helper.py replace 'console.log($MSG)' 'logger.info($MSG)' --lang ts src/
+python scripts/ast_grep_helper.py replace 'console.log($MSG)' 'logger.info($MSG)' --lang ts src/
 
 # Actually apply
-python3 scripts/ast_grep_helper.py replace 'console.log($MSG)' 'logger.info($MSG)' --lang ts src/ --apply
+python scripts/ast_grep_helper.py replace 'console.log($MSG)' 'logger.info($MSG)' --lang ts src/ --apply
 ```
 
 The helper:
@@ -113,16 +113,16 @@ The helper:
 
 ```bash
 # Discover sgconfig.yml from cwd and run all rules
-python3 scripts/ast_grep_helper.py scan src/
+python scripts/ast_grep_helper.py scan src/
 
 # Run a single rule file
-python3 scripts/ast_grep_helper.py scan -r rules/no-console.yml src/
+python scripts/ast_grep_helper.py scan -r rules/no-console.yml src/
 
 # Apply auto-fixes
-python3 scripts/ast_grep_helper.py scan -U src/
+python scripts/ast_grep_helper.py scan -U src/
 
 # CI-friendly GitHub annotations
-python3 scripts/ast_grep_helper.py scan --report-style short src/
+python scripts/ast_grep_helper.py scan --report-style short src/
 ```
 
 ### `validate` — offline pattern check (no `sg` call)
@@ -130,19 +130,19 @@ python3 scripts/ast_grep_helper.py scan --report-style short src/
 Useful for CI lints, pre-commit hooks, and quick sanity checks:
 
 ```bash
-python3 scripts/ast_grep_helper.py validate '\w+' --lang ts
+python scripts/ast_grep_helper.py validate '\w+' --lang ts
 # → exit 2: regex \w not supported. Use $VAR for identifiers.
 
-python3 scripts/ast_grep_helper.py validate 'console.log($MSG)' --lang ts
+python scripts/ast_grep_helper.py validate 'console.log($MSG)' --lang ts
 # → exit 0: pattern looks plausible for ast-grep.
 ```
 
 ### `langs` / `doctor` / `install`
 
 ```bash
-python3 scripts/ast_grep_helper.py langs       # list 25 supported languages and aliases
-python3 scripts/ast_grep_helper.py doctor      # check ast-grep binary availability
-python3 scripts/ast_grep_helper.py install     # delegate to install.sh / install.ps1
+python scripts/ast_grep_helper.py langs       # list 25 supported languages and aliases
+python scripts/ast_grep_helper.py doctor      # check ast-grep binary availability
+python scripts/ast_grep_helper.py install     # delegate to install.sh / install.ps1
 ```
 
 `new` and `test` subcommands proxy directly to `sg new` and `sg test`.
diff --git a/optional-skills/software-development/rest-graphql-debug/SKILL.md b/optional-skills/software-development/rest-graphql-debug/SKILL.md
index 90496adc73df8..ee46fedd1f945 100644
--- a/optional-skills/software-development/rest-graphql-debug/SKILL.md
+++ b/optional-skills/software-development/rest-graphql-debug/SKILL.md
@@ -59,7 +59,7 @@ terminal("""curl -X POST https://api.example.com/users \\
 terminal('curl -sI https://api.example.com/health')
 
 # Pretty-print JSON
-terminal('curl -s https://api.example.com/users | python3 -m json.tool')
+terminal('curl -s https://api.example.com/users | python -m json.tool')
 ```
 
 ### GraphQL via terminal
diff --git a/optional-skills/web-development/cloudflare-temporary-deploy/SKILL.md b/optional-skills/web-development/cloudflare-temporary-deploy/SKILL.md
index 187a048211318..5ca4f7e5a09ed 100644
--- a/optional-skills/web-development/cloudflare-temporary-deploy/SKILL.md
+++ b/optional-skills/web-development/cloudflare-temporary-deploy/SKILL.md
@@ -72,7 +72,7 @@ Use the `terminal` tool for every step. Always pin the version (`wrangler@latest
 
 3. **Parse the URLs** from that output. Run the helper to extract them reliably instead of eyeballing:
    ```
-   npx wrangler@latest deploy --temporary 2>&1 | python3 scripts/parse_deploy_output.py
+   npx wrangler@latest deploy --temporary 2>&1 | python scripts/parse_deploy_output.py
    ```
    (Resolve `scripts/parse_deploy_output.py` to this skill's absolute path.) It prints JSON: `{"live_url", "claim_url", "account", "account_state", "expires_minutes", "deployed"}`.
 
@@ -91,7 +91,7 @@ Use the `terminal` tool for every step. Always pin the version (`wrangler@latest
 |---|---|
 | Check version (need 4.102.0+) | `npx wrangler@latest --version` |
 | Deploy (no account) | `npx wrangler@latest deploy --temporary` |
-| Deploy + parse URLs | `npx wrangler@latest deploy --temporary 2>&1 \| python3 scripts/parse_deploy_output.py` |
+| Deploy + parse URLs | `npx wrangler@latest deploy --temporary 2>&1 \| python scripts/parse_deploy_output.py` |
 | Verify live | `curl -sS <live_url>` |
 | Clear cached temp account | `npx wrangler@latest logout` |
 
@@ -124,4 +124,4 @@ Use the `terminal` tool for every step. Always pin the version (`wrangler@latest
 - `npx wrangler@latest deploy --temporary` prints a `workers.dev` live URL and a `claim-preview?claimToken=` claim URL.
 - `curl -sS <live_url>` returns the exact body the Worker code produces.
 - A second deploy reports `Account: <name> (reused)` and the live URL is unchanged.
-- The parser script's self-test passes: `python3 scripts/parse_deploy_output.py --selftest`.
+- The parser script's self-test passes: `python scripts/parse_deploy_output.py --selftest`.
diff --git a/skills/autonomous-ai-agents/claude-code/SKILL.md b/skills/autonomous-ai-agents/claude-code/SKILL.md
index 7b5c7521519c6..17d499cca74db 100644
--- a/skills/autonomous-ai-agents/claude-code/SKILL.md
+++ b/skills/autonomous-ai-agents/claude-code/SKILL.md
@@ -212,7 +212,7 @@ Parse `structured_output` from the JSON result. Claude validates output against
 terminal(command="claude -p 'Start refactoring the database layer' --output-format json --max-turns 10 > /tmp/session.json", workdir="/project", timeout=180)
 
 # Resume with session ID
-terminal(command="claude -p 'Continue and add connection pooling' --resume $(cat /tmp/session.json | python3 -c 'import json,sys; print(json.load(sys.stdin)[\"session_id\"])') --max-turns 5", workdir="/project", timeout=120)
+terminal(command="claude -p 'Continue and add connection pooling' --resume $(cat /tmp/session.json | python -c 'import json,sys; print(json.load(sys.stdin)[\"session_id\"])') --max-turns 5", workdir="/project", timeout=120)
 
 # Or resume the most recent session in the same directory
 terminal(command="claude -p 'What did you do last time?' --continue --max-turns 1", workdir="/project", timeout=30)
@@ -722,7 +722,7 @@ Use `/context` in interactive mode to see a colored grid of context usage. Key t
 2. **`--dangerously-skip-permissions` dialog defaults to "No, exit"** — you must send Down then Enter to accept. Print mode (`-p`) skips this entirely.
 3. **`--max-budget-usd` minimum is ~$0.05** — system prompt cache creation alone costs this much. Setting lower will error immediately.
 4. **`--max-turns` is print-mode only** — ignored in interactive sessions.
-5. **Claude may use `python` instead of `python3`** — on systems without a `python` symlink, Claude's bash commands will fail on first try but it self-corrects.
+5. **Claude may use `python` instead of `python`** — on systems without a `python` symlink, Claude's bash commands will fail on first try but it self-corrects.
 6. **Session resumption requires same directory** — `--continue` finds the most recent session for the current working directory.
 7. **`--json-schema` needs enough `--max-turns`** — Claude must read files before producing structured output, which takes multiple turns.
 8. **Trust dialog only appears once per directory** — first-time only, then cached.
diff --git a/skills/creative/ascii-art/SKILL.md b/skills/creative/ascii-art/SKILL.md
index c3b5c7fb27472..dd9a88b8c3f0c 100644
--- a/skills/creative/ascii-art/SKILL.md
+++ b/skills/creative/ascii-art/SKILL.md
@@ -30,9 +30,9 @@ pip install pyfiglet --break-system-packages -q
 ### Usage
 
 ```bash
-python3 -m pyfiglet "YOUR TEXT" -f slant
-python3 -m pyfiglet "TEXT" -f doom -w 80    # Set width
-python3 -m pyfiglet --list_fonts             # List all 571 fonts
+python -m pyfiglet "YOUR TEXT" -f slant
+python -m pyfiglet "TEXT" -f doom -w 80    # Set width
+python -m pyfiglet --list_fonts             # List all 571 fonts
 ```
 
 ### Recommended fonts
@@ -156,7 +156,7 @@ boxes -l                                       # List all 70+ designs
 ### Combine with pyfiglet or asciified
 
 ```bash
-python3 -m pyfiglet "HERMES" -f slant | boxes -d stone
+python -m pyfiglet "HERMES" -f slant | boxes -d stone
 # Or without pyfiglet installed:
 curl -s "https://asciified.thelicato.io/api/v2/ascii?text=HERMES&font=Slant" | boxes -d stone
 ```
diff --git a/skills/creative/comfyui/SKILL.md b/skills/creative/comfyui/SKILL.md
index ac6e0f9ee262b..0db5b97cc1c36 100644
--- a/skills/creative/comfyui/SKILL.md
+++ b/skills/creative/comfyui/SKILL.md
@@ -7,7 +7,7 @@ license: MIT
 platforms: [macos, linux, windows]
 compatibility: "Requires ComfyUI (local, Comfy Desktop, or Comfy Cloud) and comfy-cli (auto-installed via pipx/uvx by the setup script)."
 prerequisites:
-  commands: ["python3"]
+  commands: ["python"]
 setup:
   help: "Run scripts/hardware_check.py FIRST to decide local vs Comfy Cloud; then scripts/comfyui_setup.sh auto-installs locally (or use Cloud API key for platform.comfy.org)."
 metadata:
@@ -108,7 +108,7 @@ command -v comfy >/dev/null 2>&1 && echo "comfy-cli: installed"
 curl -s http://127.0.0.1:8188/system_stats 2>/dev/null && echo "server: running"
 
 # Can this machine run ComfyUI locally? (GPU/VRAM/disk check)
-python3 scripts/hardware_check.py
+python scripts/hardware_check.py
 ```
 
 If nothing is installed, see **Setup & Onboarding** below — but always run the
@@ -117,7 +117,7 @@ hardware check first.
 ### One-line health check
 
 ```bash
-python3 scripts/health_check.py
+python scripts/health_check.py
 # → JSON: comfy_cli on PATH? server reachable? at least one checkpoint? smoke-test passes?
 ```
 
@@ -139,10 +139,10 @@ executable**. The scripts detect this and tell you to re-export.
 ### Step 2: See what's controllable
 
 ```bash
-python3 scripts/extract_schema.py workflow_api.json --summary-only
+python scripts/extract_schema.py workflow_api.json --summary-only
 # → {"parameter_count": 12, "has_negative_prompt": true, "has_seed": true, ...}
 
-python3 scripts/extract_schema.py workflow_api.json
+python scripts/extract_schema.py workflow_api.json
 # → full schema with parameters, model deps, embedding refs
 ```
 
@@ -150,33 +150,33 @@ python3 scripts/extract_schema.py workflow_api.json
 
 ```bash
 # Local (defaults to http://127.0.0.1:8188)
-python3 scripts/run_workflow.py \
+python scripts/run_workflow.py \
   --workflow workflow_api.json \
   --args '{"prompt": "a beautiful sunset over mountains", "seed": -1, "steps": 30}' \
   --output-dir ./outputs
 
 # Cloud (export API key once; uses correct /api routing automatically)
 export COMFY_CLOUD_API_KEY="comfyui-..."
-python3 scripts/run_workflow.py \
+python scripts/run_workflow.py \
   --workflow workflow_api.json \
   --args '{"prompt": "..."}' \
   --host https://cloud.comfy.org \
   --output-dir ./outputs
 
 # Real-time progress via WebSocket (requires `pip install websocket-client`)
-python3 scripts/run_workflow.py \
+python scripts/run_workflow.py \
   --workflow flux_dev.json \
   --args '{"prompt": "..."}' \
   --ws
 
 # img2img / inpaint: pass --input-image to upload + reference automatically
-python3 scripts/run_workflow.py \
+python scripts/run_workflow.py \
   --workflow sdxl_img2img.json \
   --input-image image=./photo.png \
   --args '{"prompt": "make it watercolor", "denoise": 0.6}'
 
 # Batch / sweep: 8 random seeds, parallel up to cloud tier limit
-python3 scripts/run_batch.py \
+python scripts/run_batch.py \
   --workflow sdxl.json \
   --args '{"prompt": "abstract"}' \
   --count 8 --randomize-seed --parallel 3 \
@@ -266,9 +266,9 @@ Routing:
 ### Step 1: Verify Hardware (ONLY if user chose local)
 
 ```bash
-python3 scripts/hardware_check.py --json
+python scripts/hardware_check.py --json
 # Optional: also probe `torch` for actual CUDA/MPS:
-python3 scripts/hardware_check.py --json --check-pytorch
+python scripts/hardware_check.py --json --check-pytorch
 ```
 
 | Verdict    | Meaning                                                       | Action |
@@ -328,7 +328,7 @@ For users without a capable GPU or who want zero setup. Hosted on RTX 6000 Pro.
    ```
 4. Run workflows:
    ```bash
-   python3 scripts/run_workflow.py \
+   python scripts/run_workflow.py \
      --workflow workflows/flux_dev_txt2img.json \
      --args '{"prompt": "..."}' \
      --host https://cloud.comfy.org \
@@ -465,13 +465,13 @@ comfy node install-deps --workflow=workflow.json   # install everything a workfl
 ### Post-Install: Verify
 
 ```bash
-python3 scripts/health_check.py
+python scripts/health_check.py
 # → comfy_cli on PATH? server reachable? checkpoints? smoke test?
 
-python3 scripts/check_deps.py my_workflow.json
+python scripts/check_deps.py my_workflow.json
 # → are this workflow's nodes/models/embeddings installed?
 
-python3 scripts/run_workflow.py \
+python scripts/run_workflow.py \
   --workflow workflows/sd15_txt2img.json \
   --args '{"prompt": "test", "steps": 4}' \
   --output-dir ./test-outputs
@@ -482,7 +482,7 @@ python3 scripts/run_workflow.py \
 The simplest way is to use `--input-image` with `run_workflow.py`:
 
 ```bash
-python3 scripts/run_workflow.py \
+python scripts/run_workflow.py \
   --workflow workflows/sdxl_img2img.json \
   --input-image image=./photo.png \
   --args '{"prompt": "make it cyberpunk", "denoise": 0.6}'
@@ -492,7 +492,7 @@ The flag uploads `photo.png`, then injects its server-side filename into
 whatever schema parameter is named `image`. For inpainting, pass both:
 
 ```bash
-python3 scripts/run_workflow.py \
+python scripts/run_workflow.py \
   --workflow workflows/sdxl_inpaint.json \
   --input-image image=./photo.png \
   --input-image mask_image=./mask.png \
@@ -536,7 +536,7 @@ curl -X POST "https://cloud.comfy.org/api/upload/image" \
 
 ```bash
 # Local
-curl -s http://127.0.0.1:8188/queue | python3 -m json.tool
+curl -s http://127.0.0.1:8188/queue | python -m json.tool
 curl -X POST http://127.0.0.1:8188/queue -d '{"clear": true}'    # cancel pending
 curl -X POST http://127.0.0.1:8188/interrupt                      # cancel running
 curl -X POST http://127.0.0.1:8188/free \
@@ -544,7 +544,7 @@ curl -X POST http://127.0.0.1:8188/free \
   -d '{"unload_models": true, "free_memory": true}'
 
 # Cloud — same paths under /api/, plus:
-python3 scripts/fetch_logs.py --tail-queue --host https://cloud.comfy.org
+python scripts/fetch_logs.py --tail-queue --host https://cloud.comfy.org
 ```
 
 ## Pitfalls
@@ -599,7 +599,7 @@ python3 scripts/fetch_logs.py --tail-queue --host https://cloud.comfy.org
 
 ## Verification Checklist
 
-Use `python3 scripts/health_check.py` to run the whole list at once. Manual:
+Use `python scripts/health_check.py` to run the whole list at once. Manual:
 
 - [ ] `hardware_check.py` verdict is `ok` OR the user explicitly chose Comfy Cloud
 - [ ] `comfy --version` works (or `uvx --from comfy-cli comfy --help`)
diff --git a/skills/creative/p5js/SKILL.md b/skills/creative/p5js/SKILL.md
index 5c4083b9a7773..4e6c7b69c9cda 100644
--- a/skills/creative/p5js/SKILL.md
+++ b/skills/creative/p5js/SKILL.md
@@ -256,7 +256,7 @@ Key implementation patterns:
 ### Step 4: Preview & Iterate
 
 - Open HTML file directly in browser — no server needed for basic sketches
-- For `loadImage()`/`loadFont()` from local files: use `scripts/serve.sh` or `python3 -m http.server`
+- For `loadImage()`/`loadFont()` from local files: use `scripts/serve.sh` or `python -m http.server`
 - Chrome DevTools Performance tab to verify 60fps
 - Test at target export resolution, not just the window size
 - Adjust parameters until the visual matches the concept from Step 1
@@ -488,7 +488,7 @@ When building p5.js sketches:
 
 1. **Write the HTML file** — single self-contained file, all code inline
 2. **Open in browser** — `open sketch.html` (macOS) or `xdg-open sketch.html` (Linux)
-3. **Local assets** (fonts, images) require a server: `python3 -m http.server 8080` in the project directory, then open `http://localhost:8080/sketch.html`
+3. **Local assets** (fonts, images) require a server: `python -m http.server 8080` in the project directory, then open `http://localhost:8080/sketch.html`
 4. **Export PNG/GIF** — add `keyPressed()` shortcuts as shown above, tell the user which key to press
 5. **Headless export** — `node scripts/export-frames.js sketch.html --frames 300` for automated frame capture (sketch must use `noLoop()` + `_p5Ready`)
 6. **MP4 rendering** — `bash scripts/render.sh sketch.html output.mp4 --duration 30`
diff --git a/skills/creative/pretext/SKILL.md b/skills/creative/pretext/SKILL.md
index 9f743310bbbac..016b534a8fe82 100644
--- a/skills/creative/pretext/SKILL.md
+++ b/skills/creative/pretext/SKILL.md
@@ -158,7 +158,7 @@ See `templates/donut-orbit.html` and `templates/hello-orb-flow.html` for working
 4. **Tune the aesthetic** — font, palette, composition, interaction. This is the work; don't skip it.
 5. **Verify locally**:
    ```sh
-   cd <dir-with-html> && python3 -m http.server 8765
+   cd <dir-with-html> && python -m http.server 8765
    # then open http://localhost:8765/<file>.html
    ```
 6. **Check the console** — pretext will throw if `prepareWithSegments` is called with a bad font string; `Intl.Segmenter` is available in every modern browser.
@@ -194,14 +194,14 @@ See `templates/donut-orbit.html` and `templates/hello-orb-flow.html` for working
 
 ## Verification Checklist
 
-- [ ] Demo is a single self-contained `.html` file — opens by double-click or `python3 -m http.server`
+- [ ] Demo is a single self-contained `.html` file — opens by double-click or `python -m http.server`
 - [ ] `@chenglou/pretext` imported via `esm.sh` with pinned version
 - [ ] Corpus is real prose, not lorem ipsum, and matches the demo's concept
 - [ ] Font string passed to `prepare` matches the CSS font exactly
 - [ ] `prepare()` / `prepareWithSegments()` called once, not per frame
 - [ ] Dark background + considered palette — not the default white canvas
 - [ ] At least one interactive response (drag / hover / scroll / click) or idle auto-motion
-- [ ] Tested locally with `python3 -m http.server` and confirmed no console errors
+- [ ] Tested locally with `python -m http.server` and confirmed no console errors
 - [ ] 60fps on a mid-tier laptop (or graceful degradation documented)
 - [ ] One "extra mile" detail the user didn't ask for
 
diff --git a/skills/github/github-auth/SKILL.md b/skills/github/github-auth/SKILL.md
index 88e29f8d2c432..89db0eb6d5f68 100644
--- a/skills/github/github-auth/SKILL.md
+++ b/skills/github/github-auth/SKILL.md
@@ -248,7 +248,7 @@ If git credentials are already configured (via credential.helper store), the tok
 
 ```bash
 # Read from git credential store
-uv run python3 "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py"
+uv run python "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py"
 ```
 
 ### Helper: Detect Auth Method
@@ -265,7 +265,7 @@ elif _hermes_env="${HERMES_HOME:-$HOME/.hermes}/.env"; [ -f "$_hermes_env" ] &&
   export GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" "$_hermes_env" | head -1 | cut -d= -f2 | tr -d '\n\r')
   echo "AUTH_METHOD=curl"
 elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
-  export GITHUB_TOKEN=$(uv run python3 "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
+  export GITHUB_TOKEN=$(uv run python "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
   echo "AUTH_METHOD=curl"
 else
   echo "AUTH_METHOD=none"
diff --git a/skills/github/github-code-review/SKILL.md b/skills/github/github-code-review/SKILL.md
index 8f59405fb2f89..38b0989b1cfab 100644
--- a/skills/github/github-code-review/SKILL.md
+++ b/skills/github/github-code-review/SKILL.md
@@ -31,7 +31,7 @@ else
     if _hermes_env="${HERMES_HOME:-$HOME/.hermes}/.env"; [ -f "$_hermes_env" ] && grep -q "^GITHUB_TOKEN=" "$_hermes_env"; then
       GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" "$_hermes_env" | head -1 | cut -d= -f2 | tr -d '\n\r')
     elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
-      GITHUB_TOKEN=$(uv run python3 "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
+      GITHUB_TOKEN=$(uv run python "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
     fi
   fi
 fi
@@ -144,7 +144,7 @@ PR_NUMBER=123
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/pulls/$PR_NUMBER \
-  | python3 -c "
+  | python -c "
 import sys, json
 pr = json.load(sys.stdin)
 print(f\"Title: {pr['title']}\")
@@ -157,7 +157,7 @@ print(f\"Body:\n{pr['body']}\")"
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/pulls/$PR_NUMBER/files \
-  | python3 -c "
+  | python -c "
 import sys, json
 for f in json.load(sys.stdin):
     print(f\"{f['status']:10} +{f['additions']:-4} -{f['deletions']:-4}  {f['filename']}\")"
@@ -224,7 +224,7 @@ gh api repos/$OWNER/$REPO/pulls/123/comments \
 HEAD_SHA=$(curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/pulls/$PR_NUMBER \
-  | python3 -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
+  | python -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
 
 curl -s -X POST \
   -H "Authorization: token $GITHUB_TOKEN" \
@@ -254,7 +254,7 @@ gh pr review 123 --comment --body "Some suggestions, nothing blocking."
 HEAD_SHA=$(curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/pulls/$PR_NUMBER \
-  | python3 -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
+  | python -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
 
 curl -s -X POST \
   -H "Authorization: token $GITHUB_TOKEN" \
@@ -419,7 +419,7 @@ gh pr review $PR_NUMBER --request-changes --body "Found a few issues — see inl
 ```bash
 HEAD_SHA=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$GH_OWNER/$GH_REPO/pulls/$PR_NUMBER \
-  | python3 -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
+  | python -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
 
 # Build the review JSON — event is APPROVE, REQUEST_CHANGES, or COMMENT
 curl -s -X POST \
diff --git a/skills/github/github-issues/SKILL.md b/skills/github/github-issues/SKILL.md
index 415e10d449a59..39172fbb472cd 100644
--- a/skills/github/github-issues/SKILL.md
+++ b/skills/github/github-issues/SKILL.md
@@ -31,7 +31,7 @@ else
     if _hermes_env="${HERMES_HOME:-$HOME/.hermes}/.env"; [ -f "$_hermes_env" ] && grep -q "^GITHUB_TOKEN=" "$_hermes_env"; then
       GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" "$_hermes_env" | head -1 | cut -d= -f2 | tr -d '\n\r')
     elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
-      GITHUB_TOKEN=$(uv run python3 "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
+      GITHUB_TOKEN=$(uv run python "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
     fi
   fi
 fi
@@ -63,7 +63,7 @@ gh issue view 42
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/repos/$OWNER/$REPO/issues?state=open&per_page=20" \
-  | python3 -c "
+  | python -c "
 import sys, json
 for i in json.load(sys.stdin):
     if 'pull_request' not in i:  # GitHub API returns PRs in /issues too
@@ -74,7 +74,7 @@ for i in json.load(sys.stdin):
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/repos/$OWNER/$REPO/issues?state=open&labels=bug&per_page=20" \
-  | python3 -c "
+  | python -c "
 import sys, json
 for i in json.load(sys.stdin):
     if 'pull_request' not in i:
@@ -84,7 +84,7 @@ for i in json.load(sys.stdin):
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/issues/42 \
-  | python3 -c "
+  | python -c "
 import sys, json
 i = json.load(sys.stdin)
 labels = ', '.join(l['name'] for l in i['labels'])
@@ -98,7 +98,7 @@ print(f\"\n{i['body']}\")"
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/search/issues?q=authentication+error+repo:$OWNER/$REPO" \
-  | python3 -c "
+  | python -c "
 import sys, json
 for i in json.load(sys.stdin)['items']:
     print(f\"#{i['number']}  {i['state']:6}  {i['title']}\")"
@@ -206,7 +206,7 @@ curl -s -X DELETE \
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/labels \
-  | python3 -c "
+  | python -c "
 import sys, json
 for l in json.load(sys.stdin):
     print(f\"  {l['name']:30}  {l.get('description', '')}\")"
@@ -312,7 +312,7 @@ gh issue list --label "needs-triage" --state open
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/repos/$OWNER/$REPO/issues?labels=needs-triage&state=open" \
-  | python3 -c "
+  | python -c "
 import sys, json
 for i in json.load(sys.stdin):
     if 'pull_request' not in i:
@@ -346,7 +346,7 @@ gh issue list --label "wontfix" --json number --jq '.[].number' | \
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/repos/$OWNER/$REPO/issues?labels=wontfix&state=open" \
-  | python3 -c "import sys,json; [print(i['number']) for i in json.load(sys.stdin)]" \
+  | python -c "import sys,json; [print(i['number']) for i in json.load(sys.stdin)]" \
   | while read num; do
     curl -s -X PATCH \
       -H "Authorization: token $GITHUB_TOKEN" \
diff --git a/skills/github/github-pr-workflow/SKILL.md b/skills/github/github-pr-workflow/SKILL.md
index f076d08b623db..b8a71bf68f029 100644
--- a/skills/github/github-pr-workflow/SKILL.md
+++ b/skills/github/github-pr-workflow/SKILL.md
@@ -33,7 +33,7 @@ else
     if _hermes_env="${HERMES_HOME:-$HOME/.hermes}/.env"; [ -f "$_hermes_env" ] && grep -q "^GITHUB_TOKEN=" "$_hermes_env"; then
       GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" "$_hermes_env" | head -1 | cut -d= -f2 | tr -d '\n\r')
     elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
-      GITHUB_TOKEN=$(uv run python3 "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
+      GITHUB_TOKEN=$(uv run python "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
     fi
   fi
 fi
@@ -173,7 +173,7 @@ SHA=$(git rev-parse HEAD)
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/commits/$SHA/status \
-  | python3 -c "
+  | python -c "
 import sys, json
 data = json.load(sys.stdin)
 print(f\"Overall: {data['state']}\")
@@ -184,7 +184,7 @@ for s in data.get('statuses', []):
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/commits/$SHA/check-runs \
-  | python3 -c "
+  | python -c "
 import sys, json
 data = json.load(sys.stdin)
 for cr in data.get('check_runs', []):
@@ -200,7 +200,7 @@ for i in $(seq 1 20); do
   STATUS=$(curl -s \
     -H "Authorization: token $GITHUB_TOKEN" \
     https://api.github.com/repos/$OWNER/$REPO/commits/$SHA/status \
-    | python3 -c "import sys,json; print(json.load(sys.stdin)['state'])")
+    | python -c "import sys,json; print(json.load(sys.stdin)['state'])")
   echo "Check $i: $STATUS"
   if [ "$STATUS" = "success" ] || [ "$STATUS" = "failure" ] || [ "$STATUS" = "error" ]; then
     break
@@ -234,7 +234,7 @@ BRANCH=$(git branch --show-current)
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/repos/$OWNER/$REPO/actions/runs?branch=$BRANCH&per_page=5" \
-  | python3 -c "
+  | python -c "
 import sys, json
 runs = json.load(sys.stdin)['workflow_runs']
 for r in runs:
@@ -319,7 +319,7 @@ Merge methods: `"merge"` (merge commit), `"squash"`, `"rebase"`
 PR_NODE_ID=$(curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/pulls/$PR_NUMBER \
-  | python3 -c "import sys,json; print(json.load(sys.stdin)['node_id'])")
+  | python -c "import sys,json; print(json.load(sys.stdin)['node_id'])")
 
 curl -s -X POST \
   -H "Authorization: token $GITHUB_TOKEN" \
diff --git a/skills/github/github-repo-management/SKILL.md b/skills/github/github-repo-management/SKILL.md
index 54565d7a10b5a..af147a6fa44de 100644
--- a/skills/github/github-repo-management/SKILL.md
+++ b/skills/github/github-repo-management/SKILL.md
@@ -30,7 +30,7 @@ else
     if _hermes_env="${HERMES_HOME:-$HOME/.hermes}/.env"; [ -f "$_hermes_env" ] && grep -q "^GITHUB_TOKEN=" "$_hermes_env"; then
       GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" "$_hermes_env" | head -1 | cut -d= -f2 | tr -d '\n\r')
     elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
-      GITHUB_TOKEN=$(uv run python3 "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
+      GITHUB_TOKEN=$(uv run python "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
     fi
   fi
 fi
@@ -39,7 +39,7 @@ fi
 if [ "$AUTH" = "gh" ]; then
   GH_USER=$(gh api user --jq '.login')
 else
-  GH_USER=$(curl -s -H "Authorization: token $GITHUB_TOKEN" https://api.github.com/user | python3 -c "import sys,json; print(json.load(sys.stdin)['login'])")
+  GH_USER=$(curl -s -H "Authorization: token $GITHUB_TOKEN" https://api.github.com/user | python -c "import sys,json; print(json.load(sys.stdin)['login'])")
 fi
 ```
 
@@ -213,7 +213,7 @@ gh search repos "machine learning" --language python --sort stars
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO \
-  | python3 -c "
+  | python -c "
 import sys, json
 r = json.load(sys.stdin)
 print(f\"Name: {r['full_name']}\")
@@ -226,7 +226,7 @@ print(f\"Language: {r['language']}\")"
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/user/repos?per_page=20&sort=updated" \
-  | python3 -c "
+  | python -c "
 import sys, json
 for r in json.load(sys.stdin):
     vis = 'private' if r['private'] else 'public'
@@ -235,7 +235,7 @@ for r in json.load(sys.stdin):
 # Search repos
 curl -s \
   "https://api.github.com/search/repositories?q=machine+learning+language:python&sort=stars&per_page=10" \
-  | python3 -c "
+  | python -c "
 import sys, json
 for r in json.load(sys.stdin)['items']:
     print(f\"  {r['full_name']:40}  ★{r['stargazers_count']:6}  {r['description'][:60] if r['description'] else ''}\")"
@@ -321,7 +321,7 @@ curl -s \
   https://api.github.com/repos/$OWNER/$REPO/actions/secrets/public-key
 
 # Encrypt and set (requires Python with PyNaCl)
-python3 -c "
+python -c "
 from base64 import b64encode
 from nacl import encoding, public
 import json, sys
@@ -349,7 +349,7 @@ curl -s -X PUT \
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/actions/secrets \
-  | python3 -c "
+  | python -c "
 import sys, json
 for s in json.load(sys.stdin)['secrets']:
     print(f\"  {s['name']:30}  updated: {s['updated_at']}\")"
@@ -389,7 +389,7 @@ curl -s -X POST \
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/releases \
-  | python3 -c "
+  | python -c "
 import sys, json
 for r in json.load(sys.stdin):
     tag = r.get('tag_name', 'no tag')
@@ -426,7 +426,7 @@ gh workflow run deploy.yml -f environment=staging
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/repos/$OWNER/$REPO/actions/workflows \
-  | python3 -c "
+  | python -c "
 import sys, json
 for w in json.load(sys.stdin)['workflows']:
     print(f\"  {w['id']:10}  {w['name']:30}  {w['state']}\")"
@@ -435,7 +435,7 @@ for w in json.load(sys.stdin)['workflows']:
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   "https://api.github.com/repos/$OWNER/$REPO/actions/runs?per_page=10" \
-  | python3 -c "
+  | python -c "
 import sys, json
 for r in json.load(sys.stdin)['workflow_runs']:
     print(f\"  Run {r['id']}  {r['name']:30}  {r['conclusion'] or r['status']}\")"
@@ -494,7 +494,7 @@ curl -s -X POST \
 curl -s \
   -H "Authorization: token $GITHUB_TOKEN" \
   https://api.github.com/gists \
-  | python3 -c "
+  | python -c "
 import sys, json
 for g in json.load(sys.stdin):
     files = ', '.join(g['files'].keys())
diff --git a/skills/media/youtube-content/SKILL.md b/skills/media/youtube-content/SKILL.md
index 8e445f5f26745..d9a981bc4aadb 100644
--- a/skills/media/youtube-content/SKILL.md
+++ b/skills/media/youtube-content/SKILL.md
@@ -34,16 +34,16 @@ uv pip install youtube-transcript-api
 
 ```bash
 # JSON output with metadata
-uv run python3 SKILL_DIR/scripts/fetch_transcript.py "https://youtube.com/watch?v=VIDEO_ID"
+uv run python SKILL_DIR/scripts/fetch_transcript.py "https://youtube.com/watch?v=VIDEO_ID"
 
 # Plain text (good for piping into further processing)
-uv run python3 SKILL_DIR/scripts/fetch_transcript.py "URL" --text-only
+uv run python SKILL_DIR/scripts/fetch_transcript.py "URL" --text-only
 
 # With timestamps
-uv run python3 SKILL_DIR/scripts/fetch_transcript.py "URL" --timestamps
+uv run python SKILL_DIR/scripts/fetch_transcript.py "URL" --timestamps
 
 # Specific language with fallback chain
-uv run python3 SKILL_DIR/scripts/fetch_transcript.py "URL" --language tr,en
+uv run python SKILL_DIR/scripts/fetch_transcript.py "URL" --language tr,en
 ```
 
 ## Output Formats
@@ -69,7 +69,7 @@ After fetching the transcript, format it based on what the user asks for:
 
 ## Workflow
 
-1. **Fetch** the transcript using the helper script with `--text-only --timestamps` via `uv run python3`.
+1. **Fetch** the transcript using the helper script with `--text-only --timestamps` via `uv run python`.
 2. **Validate**: confirm the output is non-empty and in the expected language. If empty, retry without `--language` to get any available transcript. If still empty, tell the user the video likely has transcripts disabled.
 3. **Chunk if needed**: if the transcript exceeds ~50K characters, split into overlapping chunks (~40K with 2K overlap) and summarize each chunk before merging.
 4. **Transform** into the requested output format. If the user did not specify a format, default to a summary.
diff --git a/skills/productivity/airtable/SKILL.md b/skills/productivity/airtable/SKILL.md
index 3fa1b0ab9737e..d628c231feed3 100644
--- a/skills/productivity/airtable/SKILL.md
+++ b/skills/productivity/airtable/SKILL.md
@@ -44,10 +44,10 @@ Work with Airtable's REST API directly via `curl` using the `terminal` tool. No
 Base curl pattern:
 ```bash
 curl -s "https://api.airtable.com/v0/$BASE_ID/$TABLE?maxRecords=5" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 
-`-s` suppresses curl's progress bar — keep it set for every call so the tool output stays clean for Hermes. Pipe through `python3 -m json.tool` (always present) or `jq` (if installed) for readable JSON.
+`-s` suppresses curl's progress bar — keep it set for every call so the tool output stays clean for Hermes. Pipe through `python -m json.tool` (always present) or `jq` (if installed) for readable JSON.
 
 ## Field Types (request body shapes)
 
@@ -73,35 +73,35 @@ Pass `"typecast": true` at the top level of a create/update body to let Airtable
 ### List bases the token can see
 ```bash
 curl -s "https://api.airtable.com/v0/meta/bases" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 
 ### List tables + schema for a base
 ```bash
 curl -s "https://api.airtable.com/v0/meta/bases/$BASE_ID/tables" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 Use this BEFORE mutating — confirms exact field names and IDs, surfaces `options.choices` for select fields, and shows primary-field names.
 
 ### List records (first 10)
 ```bash
 curl -s "https://api.airtable.com/v0/$BASE_ID/$TABLE?maxRecords=10" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 
 ### Get a single record
 ```bash
 curl -s "https://api.airtable.com/v0/$BASE_ID/$TABLE/$RECORD_ID" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 
 ### Filter records (filterByFormula)
 Airtable formulas must be URL-encoded. Let Python stdlib do it — never hand-encode:
 ```bash
 FORMULA="{Status}='Todo'"
-ENC=$(python3 -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=""))' "$FORMULA")
+ENC=$(python -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=""))' "$FORMULA")
 curl -s "https://api.airtable.com/v0/$BASE_ID/$TABLE?filterByFormula=$ENC&maxRecords=20" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 
 Useful formula patterns:
@@ -115,14 +115,14 @@ Useful formula patterns:
 ### Sort + select specific fields
 ```bash
 curl -s "https://api.airtable.com/v0/$BASE_ID/$TABLE?sort%5B0%5D%5Bfield%5D=Priority&sort%5B0%5D%5Bdirection%5D=asc&fields%5B%5D=Name&fields%5B%5D=Status" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 Square brackets in query params MUST be URL-encoded (`%5B` / `%5D`).
 
 ### Use a named view
 ```bash
 curl -s "https://api.airtable.com/v0/$BASE_ID/$TABLE?view=Grid%20view&maxRecords=50" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 Views apply their saved filter + sort server-side.
 
@@ -133,7 +133,7 @@ Views apply their saved filter + sort server-side.
 curl -s -X POST "https://api.airtable.com/v0/$BASE_ID/$TABLE" \
   -H "Authorization: Bearer $AIRTABLE_API_KEY" \
   -H "Content-Type: application/json" \
-  -d '{"fields":{"Name":"New task","Status":"Todo","Priority":"High"}}' | python3 -m json.tool
+  -d '{"fields":{"Name":"New task","Status":"Todo","Priority":"High"}}' | python -m json.tool
 ```
 
 ### Create up to 10 records in one call
@@ -147,7 +147,7 @@ curl -s -X POST "https://api.airtable.com/v0/$BASE_ID/$TABLE" \
       {"fields": {"Name": "Task A", "Status": "Todo"}},
       {"fields": {"Name": "Task B", "Status": "In progress"}}
     ]
-  }' | python3 -m json.tool
+  }' | python -m json.tool
 ```
 Batch endpoints are capped at **10 records per request**. For larger inserts, loop in batches of 10 with a short sleep to respect 5 req/sec/base.
 
@@ -156,7 +156,7 @@ Batch endpoints are capped at **10 records per request**. For larger inserts, lo
 curl -s -X PATCH "https://api.airtable.com/v0/$BASE_ID/$TABLE/$RECORD_ID" \
   -H "Authorization: Bearer $AIRTABLE_API_KEY" \
   -H "Content-Type: application/json" \
-  -d '{"fields":{"Status":"Done"}}' | python3 -m json.tool
+  -d '{"fields":{"Status":"Done"}}' | python -m json.tool
 ```
 
 ### Upsert by a merge field (no ID needed)
@@ -169,20 +169,20 @@ curl -s -X PATCH "https://api.airtable.com/v0/$BASE_ID/$TABLE" \
     "records": [
       {"fields": {"Email": "user@example.com", "Status": "Active"}}
     ]
-  }' | python3 -m json.tool
+  }' | python -m json.tool
 ```
 `performUpsert` creates records whose merge-field values are new, patches records whose merge-field values already exist. Great for idempotent syncs.
 
 ### Delete a record
 ```bash
 curl -s -X DELETE "https://api.airtable.com/v0/$BASE_ID/$TABLE/$RECORD_ID" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 
 ### Delete up to 10 records in one call
 ```bash
 curl -s -X DELETE "https://api.airtable.com/v0/$BASE_ID/$TABLE?records%5B%5D=rec1&records%5B%5D=rec2" \
-  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python3 -m json.tool
+  -H "Authorization: Bearer $AIRTABLE_API_KEY" | python -m json.tool
 ```
 
 ## Pagination
@@ -195,8 +195,8 @@ while :; do
   URL="https://api.airtable.com/v0/$BASE_ID/$TABLE?pageSize=100"
   [ -n "$OFFSET" ] && URL="$URL&offset=$OFFSET"
   RESP=$(curl -s "$URL" -H "Authorization: Bearer $AIRTABLE_API_KEY")
-  echo "$RESP" | python3 -c 'import json,sys; d=json.load(sys.stdin); [print(r["id"], r["fields"].get("Name","")) for r in d["records"]]'
-  OFFSET=$(echo "$RESP" | python3 -c 'import json,sys; d=json.load(sys.stdin); print(d.get("offset",""))')
+  echo "$RESP" | python -c 'import json,sys; d=json.load(sys.stdin); [print(r["id"], r["fields"].get("Name","")) for r in d["records"]]'
+  OFFSET=$(echo "$RESP" | python -c 'import json,sys; d=json.load(sys.stdin); print(d.get("offset",""))')
   [ -z "$OFFSET" ] && break
 done
 ```
@@ -223,7 +223,7 @@ done
 
 - **Always use the `terminal` tool with `curl`.** Do NOT use `web_extract` (it can't send auth headers) or `browser_navigate` (needs UI auth and is slow).
 - **`AIRTABLE_API_KEY` flows from `${HERMES_HOME:-~/.hermes}/.env` into the subprocess automatically** when this skill is loaded — no need to re-export it before each `curl` call.
-- **Escape curly braces in formulas carefully.** In a heredoc body, `{Status}` is literal. In a shell argument, `{Status}` is safe outside `{...}` brace-expansion context — but pass dynamic strings through `python3 urllib.parse.quote` before splicing into a URL.
-- **Pretty-print with `python3 -m json.tool`** (always present) rather than `jq` (optional). Only reach for `jq` when you need filtering/projection.
+- **Escape curly braces in formulas carefully.** In a heredoc body, `{Status}` is literal. In a shell argument, `{Status}` is safe outside `{...}` brace-expansion context — but pass dynamic strings through `python urllib.parse.quote` before splicing into a URL.
+- **Pretty-print with `python -m json.tool`** (always present) rather than `jq` (optional). Only reach for `jq` when you need filtering/projection.
 - **Pagination is per-page, not global.** Airtable's 100-record cap is a hard limit; there is no way to bump it. Loop with `offset` until the field is absent.
 - **Read the `errors` array** on non-2xx responses — Airtable returns structured error codes like `AUTHENTICATION_REQUIRED`, `INVALID_PERMISSIONS`, `MODEL_ID_NOT_FOUND`, `INVALID_MULTIPLE_CHOICE_OPTIONS` that tell you exactly what's wrong.
diff --git a/skills/productivity/maps/SKILL.md b/skills/productivity/maps/SKILL.md
index 3c1e8af3dfbca..635f211741ead 100644
--- a/skills/productivity/maps/SKILL.md
+++ b/skills/productivity/maps/SKILL.md
@@ -50,8 +50,8 @@ MAPS=~/.hermes/skills/maps/scripts/maps_client.py
 ### search — Geocode a place name
 
 ```bash
-python3 $MAPS search "Eiffel Tower"
-python3 $MAPS search "1600 Pennsylvania Ave, Washington DC"
+python $MAPS search "Eiffel Tower"
+python $MAPS search "1600 Pennsylvania Ave, Washington DC"
 ```
 
 Returns: lat, lon, display name, type, bounding box, importance score.
@@ -59,7 +59,7 @@ Returns: lat, lon, display name, type, bounding box, importance score.
 ### reverse — Coordinates to address
 
 ```bash
-python3 $MAPS reverse 48.8584 2.2945
+python $MAPS reverse 48.8584 2.2945
 ```
 
 Returns: full address breakdown (street, city, state, country, postcode).
@@ -68,15 +68,15 @@ Returns: full address breakdown (street, city, state, country, postcode).
 
 ```bash
 # By coordinates (from a Telegram location pin, for example)
-python3 $MAPS nearby 48.8584 2.2945 restaurant --limit 10
-python3 $MAPS nearby 40.7128 -74.0060 hospital --radius 2000
+python $MAPS nearby 48.8584 2.2945 restaurant --limit 10
+python $MAPS nearby 40.7128 -74.0060 hospital --radius 2000
 
 # By address / city / zip / landmark — --near auto-geocodes
-python3 $MAPS nearby --near "Times Square, New York" --category cafe
-python3 $MAPS nearby --near "90210" --category pharmacy
+python $MAPS nearby --near "Times Square, New York" --category cafe
+python $MAPS nearby --near "90210" --category pharmacy
 
 # Multiple categories merged into one query
-python3 $MAPS nearby --near "downtown austin" --category restaurant --category bar --limit 10
+python $MAPS nearby --near "downtown austin" --category restaurant --category bar --limit 10
 ```
 
 46 categories: restaurant, cafe, bar, hospital, pharmacy, hotel, guest_house,
@@ -95,9 +95,9 @@ directions from the search point), and promoted tags when available —
 ### distance — Travel distance and time
 
 ```bash
-python3 $MAPS distance "Paris" --to "Lyon"
-python3 $MAPS distance "New York" --to "Boston" --mode driving
-python3 $MAPS distance "Big Ben" --to "Tower Bridge" --mode walking
+python $MAPS distance "Paris" --to "Lyon"
+python $MAPS distance "New York" --to "Boston" --mode driving
+python $MAPS distance "Big Ben" --to "Tower Bridge" --mode walking
 ```
 
 Modes: driving (default), walking, cycling. Returns road distance, duration,
@@ -106,8 +106,8 @@ and straight-line distance for comparison.
 ### directions — Turn-by-turn navigation
 
 ```bash
-python3 $MAPS directions "Eiffel Tower" --to "Louvre Museum" --mode walking
-python3 $MAPS directions "JFK Airport" --to "Times Square" --mode driving
+python $MAPS directions "Eiffel Tower" --to "Louvre Museum" --mode walking
+python $MAPS directions "JFK Airport" --to "Times Square" --mode driving
 ```
 
 Returns numbered steps with instruction, distance, duration, road name, and
@@ -116,8 +116,8 @@ maneuver type (turn, depart, arrive, etc.).
 ### timezone — Timezone for coordinates
 
 ```bash
-python3 $MAPS timezone 48.8584 2.2945
-python3 $MAPS timezone 35.6762 139.6503
+python $MAPS timezone 48.8584 2.2945
+python $MAPS timezone 35.6762 139.6503
 ```
 
 Returns timezone name, UTC offset, and current local time.
@@ -125,8 +125,8 @@ Returns timezone name, UTC offset, and current local time.
 ### area — Bounding box and area for a place
 
 ```bash
-python3 $MAPS area "Manhattan, New York"
-python3 $MAPS area "London"
+python $MAPS area "Manhattan, New York"
+python $MAPS area "London"
 ```
 
 Returns bounding box coordinates, width/height in km, and approximate area.
@@ -135,7 +135,7 @@ Useful as input for the bbox command.
 ### bbox — Search within a bounding box
 
 ```bash
-python3 $MAPS bbox 40.75 -74.00 40.77 -73.98 restaurant --limit 20
+python $MAPS bbox 40.75 -74.00 40.77 -73.98 restaurant --limit 20
 ```
 
 Finds POIs within a geographic rectangle. Use `area` first to get the
@@ -148,7 +148,7 @@ When a user sends a location pin, the message contains `latitude:` and
 
 ```bash
 # User sent a pin at 36.17, -115.14 and asked "find cafes nearby"
-python3 $MAPS nearby 36.17 -115.14 cafe --radius 1500
+python $MAPS nearby 36.17 -115.14 cafe --radius 1500
 ```
 
 Present results as a numbered list with names, distances, and the
@@ -187,9 +187,9 @@ current.
 ## Verification
 
 ```bash
-python3 ~/.hermes/skills/maps/scripts/maps_client.py search "Statue of Liberty"
+python ~/.hermes/skills/maps/scripts/maps_client.py search "Statue of Liberty"
 # Should return lat ~40.689, lon ~-74.044
 
-python3 ~/.hermes/skills/maps/scripts/maps_client.py nearby --near "Times Square" --category restaurant --limit 3
+python ~/.hermes/skills/maps/scripts/maps_client.py nearby --near "Times Square" --category restaurant --limit 3
 # Should return a list of restaurants within ~500m of Times Square
 ```
diff --git a/skills/productivity/ocr-and-documents/SKILL.md b/skills/productivity/ocr-and-documents/SKILL.md
index 5d7278fa07a78..0677b70a1598f 100644
--- a/skills/productivity/ocr-and-documents/SKILL.md
+++ b/skills/productivity/ocr-and-documents/SKILL.md
@@ -77,7 +77,7 @@ python scripts/extract_pymupdf.py document.pdf --pages 0-4   # Specific pages
 
 **Inline**:
 ```bash
-python3 -c "
+python -c "
 import pymupdf
 doc = pymupdf.open('document.pdf')
 for page in doc:
diff --git a/skills/productivity/pdf/SKILL.md b/skills/productivity/pdf/SKILL.md
index 4c6cf343aeba8..a10b25fdca78c 100644
--- a/skills/productivity/pdf/SKILL.md
+++ b/skills/productivity/pdf/SKILL.md
@@ -29,8 +29,8 @@ Create PDFs from structured specs, build and fill AcroForm forms (with layout li
 ## Prerequisites
 
 - Python 3.10+ with `pypdf`, `reportlab`, `pdfplumber`:
-  `python3 -m pip install pypdf reportlab pdfplumber`
-- Optional, for page rasterization (`pdf_page_image.py`, overlay rendering): `python3 -m pip install pypdfium2`, or poppler's `pdftoppm` on PATH. Scripts fall back pypdfium2 → pdftoppm and report `{"rendered": false, "missing": [...]}` (exit 0) when neither exists.
+  `python -m pip install pypdf reportlab pdfplumber`
+- Optional, for page rasterization (`pdf_page_image.py`, overlay rendering): `python -m pip install pypdfium2`, or poppler's `pdftoppm` on PATH. Scripts fall back pypdfium2 → pdftoppm and report `{"rendered": false, "missing": [...]}` (exit 0) when neither exists.
 - Each helper script checks imports lazily and prints an install hint if a dependency is missing.
 
 ## How to Run
@@ -38,27 +38,27 @@ Create PDFs from structured specs, build and fill AcroForm forms (with layout li
 All helpers live in `scripts/` and are argparse CLIs — run them with the `terminal` tool; every one supports `--help`. They read/write JSON strictly as UTF-8, print JSON results to stdout, and exit non-zero on failure.
 
 ```bash
-python3 scripts/pdf_create.py spec.json -o out.pdf         # build PDF from JSON spec
-python3 scripts/pdf_make_form.py formspec.json -o form.pdf # build fillable AcroForm from JSON spec
-python3 scripts/pdf_form_layout.py formspec.json           # lint form layout BEFORE building
-python3 scripts/pdf_form_layout.py formspec.json --render-overlay boxes.png [--pdf form.pdf]
-python3 scripts/pdf_read.py doc.pdf --text                 # per-page text (JSON)
-python3 scripts/pdf_read.py doc.pdf --tables --csv-dir t/  # tables to JSON + CSV files
-python3 scripts/pdf_read.py doc.pdf --meta                 # metadata, page sizes, encrypted/scanned flags
-python3 scripts/pdf_read.py form.pdf --fields              # form fields: name, type, value
-python3 scripts/pdf_merge.py a.pdf b.pdf -o merged.pdf [--bookmarks]
-python3 scripts/pdf_split.py doc.pdf --pages 1-3,7 -o part.pdf [--rotate 90]
-python3 scripts/pdf_fill_form.py form.pdf --fields-json values.json -o filled.pdf [--flatten]
-python3 scripts/pdf_secure.py doc.pdf --encrypt -o enc.pdf --user-password your-password
-python3 scripts/pdf_secure.py enc.pdf --decrypt -o dec.pdf --password your-password
-python3 scripts/pdf_watermark.py doc.pdf --stamp mark.pdf -o stamped.pdf [--under]
-python3 scripts/pdf_stamp.py doc.pdf -o out.pdf --text "DRAFT" --x 150 --y 400 \
+python scripts/pdf_create.py spec.json -o out.pdf         # build PDF from JSON spec
+python scripts/pdf_make_form.py formspec.json -o form.pdf # build fillable AcroForm from JSON spec
+python scripts/pdf_form_layout.py formspec.json           # lint form layout BEFORE building
+python scripts/pdf_form_layout.py formspec.json --render-overlay boxes.png [--pdf form.pdf]
+python scripts/pdf_read.py doc.pdf --text                 # per-page text (JSON)
+python scripts/pdf_read.py doc.pdf --tables --csv-dir t/  # tables to JSON + CSV files
+python scripts/pdf_read.py doc.pdf --meta                 # metadata, page sizes, encrypted/scanned flags
+python scripts/pdf_read.py form.pdf --fields              # form fields: name, type, value
+python scripts/pdf_merge.py a.pdf b.pdf -o merged.pdf [--bookmarks]
+python scripts/pdf_split.py doc.pdf --pages 1-3,7 -o part.pdf [--rotate 90]
+python scripts/pdf_fill_form.py form.pdf --fields-json values.json -o filled.pdf [--flatten]
+python scripts/pdf_secure.py doc.pdf --encrypt -o enc.pdf --user-password your-password
+python scripts/pdf_secure.py enc.pdf --decrypt -o dec.pdf --password your-password
+python scripts/pdf_watermark.py doc.pdf --stamp mark.pdf -o stamped.pdf [--under]
+python scripts/pdf_stamp.py doc.pdf -o out.pdf --text "DRAFT" --x 150 --y 400 \
     --font-size 60 --rotation 45 --opacity 0.3 --color "#cc0000" [--pages 1-3]
-python3 scripts/pdf_stamp.py doc.pdf -o out.pdf --image sig.png --x 400 --y 60 --width 120
-python3 scripts/pdf_page_image.py doc.pdf --pages 1-3 --dpi 150 --out-dir imgs/
-python3 scripts/pdf_meta.py doc.pdf --set-meta --title "T" --author "A" -o out.pdf
-python3 scripts/pdf_meta.py doc.pdf --attach data.csv -o out.pdf
-python3 scripts/pdf_meta.py doc.pdf --list-attachments | --extract-attachments dir/
+python scripts/pdf_stamp.py doc.pdf -o out.pdf --image sig.png --x 400 --y 60 --width 120
+python scripts/pdf_page_image.py doc.pdf --pages 1-3 --dpi 150 --out-dir imgs/
+python scripts/pdf_meta.py doc.pdf --set-meta --title "T" --author "A" -o out.pdf
+python scripts/pdf_meta.py doc.pdf --attach data.csv -o out.pdf
+python scripts/pdf_meta.py doc.pdf --list-attachments | --extract-attachments dir/
 ```
 
 ## Quick Reference
diff --git a/skills/productivity/powerpoint/SKILL.md b/skills/productivity/powerpoint/SKILL.md
index 0fa88debd6d16..4d73a518aa5b1 100644
--- a/skills/productivity/powerpoint/SKILL.md
+++ b/skills/productivity/powerpoint/SKILL.md
@@ -41,7 +41,7 @@ and slide rendering — all offline, no PowerPoint installation required.
   gracefully (reports `{"rendered": false, "missing": [...]}`, exit 0)
   when absent — all create/read/edit operations work without them.
 - Check availability via `terminal`:
-  `python3 -c "import pptx; print(pptx.__version__)"` and `which soffice pdftoppm`.
+  `python -c "import pptx; print(pptx.__version__)"` and `which soffice pdftoppm`.
 
 ## How to Run
 
@@ -49,16 +49,16 @@ All scripts live in `scripts/`, take `--help`, print JSON to stdout, and
 exit non-zero on failure. Run them with `terminal`:
 
 ```bash
-python3 scripts/pptx_create.py deck.json out.pptx
-python3 scripts/pptx_read.py deck.pptx --outline      # full JSON outline
-python3 scripts/pptx_read.py deck.pptx --notes        # speaker notes
-python3 scripts/pptx_read.py deck.pptx --images ./img # export pictures
-python3 scripts/pptx_edit.py deck.pptx --replace-text "Old Corp" "New Corp"
-python3 scripts/pptx_edit.py deck.pptx --chart-data update.json
-python3 scripts/pptx_edit.py deck.pptx --duplicate-slide 2
-python3 scripts/pptx_edit.py deck.pptx --remove-slide 3 --move-slide 2 0
-python3 scripts/pptx_from_template.py brand.pptx out.pptx --values vals.json
-python3 scripts/pptx_render.py deck.pptx --outdir ./render  # slide PNGs
+python scripts/pptx_create.py deck.json out.pptx
+python scripts/pptx_read.py deck.pptx --outline      # full JSON outline
+python scripts/pptx_read.py deck.pptx --notes        # speaker notes
+python scripts/pptx_read.py deck.pptx --images ./img # export pictures
+python scripts/pptx_edit.py deck.pptx --replace-text "Old Corp" "New Corp"
+python scripts/pptx_edit.py deck.pptx --chart-data update.json
+python scripts/pptx_edit.py deck.pptx --duplicate-slide 2
+python scripts/pptx_edit.py deck.pptx --remove-slide 3 --move-slide 2 0
+python scripts/pptx_from_template.py brand.pptx out.pptx --values vals.json
+python scripts/pptx_render.py deck.pptx --outdir ./render  # slide PNGs
 ```
 
 Author JSON specs with `write_file`; inspect script output and generated
@@ -217,4 +217,4 @@ say so rather than approximating.
    shapes, truncated text, and color problems the outline cannot. If the
    render tools are missing, the script says so; rely on the outline.
 4. The bundled test suite is the full contract:
-   `python3 -m pytest tests/ -q` (requires python-pptx + pytest).
+   `python -m pytest tests/ -q` (requires python-pptx + pytest).
diff --git a/skills/research/arxiv/SKILL.md b/skills/research/arxiv/SKILL.md
index 70ab36eba2480..e3e6ac738f7b5 100644
--- a/skills/research/arxiv/SKILL.md
+++ b/skills/research/arxiv/SKILL.md
@@ -26,7 +26,7 @@ Search and retrieve academic papers from arXiv via their free REST API. No API k
 
 ## Searching Papers
 
-The API returns Atom XML. Parse with `grep`/`sed` or pipe through `python3` for clean output.
+The API returns Atom XML. Parse with `grep`/`sed` or pipe through `python` for clean output.
 
 ### Basic search
 
@@ -37,7 +37,7 @@ curl -s "https://export.arxiv.org/api/query?search_query=all:GRPO+reinforcement+
 ### Clean output (parse XML to readable format)
 
 ```bash
-curl -s "https://export.arxiv.org/api/query?search_query=all:GRPO+reinforcement+learning&max_results=5&sortBy=submittedDate&sortOrder=descending" | python3 -c "
+curl -s "https://export.arxiv.org/api/query?search_query=all:GRPO+reinforcement+learning&max_results=5&sortBy=submittedDate&sortOrder=descending" | python -c "
 import sys, xml.etree.ElementTree as ET
 ns = {'a': 'http://www.w3.org/2005/Atom'}
 root = ET.parse(sys.stdin).getroot()
@@ -117,7 +117,7 @@ After fetching metadata for a paper, generate a BibTeX entry:
 
 {% raw %}
 ```bash
-curl -s "https://export.arxiv.org/api/query?id_list=1706.03762" | python3 -c "
+curl -s "https://export.arxiv.org/api/query?id_list=1706.03762" | python -c "
 import sys, xml.etree.ElementTree as ET
 ns = {'a': 'http://www.w3.org/2005/Atom', 'arxiv': 'http://arxiv.org/schemas/atom'}
 root = ET.parse(sys.stdin).getroot()
@@ -197,7 +197,7 @@ arXiv doesn't provide citation data or recommendations. Use the **Semantic Schol
 
 ```bash
 # By arXiv ID
-curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:2402.03300?fields=title,authors,citationCount,referenceCount,influentialCitationCount,year,abstract" | python3 -m json.tool
+curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:2402.03300?fields=title,authors,citationCount,referenceCount,influentialCitationCount,year,abstract" | python -m json.tool
 
 # By Semantic Scholar paper ID or DOI
 curl -s "https://api.semanticscholar.org/graph/v1/paper/DOI:10.1234/example?fields=title,citationCount"
@@ -206,19 +206,19 @@ curl -s "https://api.semanticscholar.org/graph/v1/paper/DOI:10.1234/example?fiel
 ### Get citations OF a paper (who cited it)
 
 ```bash
-curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:2402.03300/citations?fields=title,authors,year,citationCount&limit=10" | python3 -m json.tool
+curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:2402.03300/citations?fields=title,authors,year,citationCount&limit=10" | python -m json.tool
 ```
 
 ### Get references FROM a paper (what it cites)
 
 ```bash
-curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:2402.03300/references?fields=title,authors,year,citationCount&limit=10" | python3 -m json.tool
+curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:2402.03300/references?fields=title,authors,year,citationCount&limit=10" | python -m json.tool
 ```
 
 ### Search papers (alternative to arXiv search, returns JSON)
 
 ```bash
-curl -s "https://api.semanticscholar.org/graph/v1/paper/search?query=GRPO+reinforcement+learning&limit=5&fields=title,authors,year,citationCount,externalIds" | python3 -m json.tool
+curl -s "https://api.semanticscholar.org/graph/v1/paper/search?query=GRPO+reinforcement+learning&limit=5&fields=title,authors,year,citationCount,externalIds" | python -m json.tool
 ```
 
 ### Get paper recommendations
@@ -226,13 +226,13 @@ curl -s "https://api.semanticscholar.org/graph/v1/paper/search?query=GRPO+reinfo
 ```bash
 curl -s -X POST "https://api.semanticscholar.org/recommendations/v1/papers/" \
   -H "Content-Type: application/json" \
-  -d '{"positivePaperIds": ["arXiv:2402.03300"], "negativePaperIds": []}' | python3 -m json.tool
+  -d '{"positivePaperIds": ["arXiv:2402.03300"], "negativePaperIds": []}' | python -m json.tool
 ```
 
 ### Author profile
 
 ```bash
-curl -s "https://api.semanticscholar.org/graph/v1/author/search?query=Yann+LeCun&fields=name,hIndex,citationCount,paperCount" | python3 -m json.tool
+curl -s "https://api.semanticscholar.org/graph/v1/author/search?query=Yann+LeCun&fields=name,hIndex,citationCount,paperCount" | python -m json.tool
 ```
 
 ### Useful Semantic Scholar fields
@@ -261,7 +261,7 @@ curl -s "https://api.semanticscholar.org/graph/v1/author/search?query=Yann+LeCun
 ## Notes
 
 - arXiv returns Atom XML — use the helper script or parsing snippet for clean output
-- Semantic Scholar returns JSON — pipe through `python3 -m json.tool` for readability
+- Semantic Scholar returns JSON — pipe through `python -m json.tool` for readability
 - arXiv IDs: old format (`hep-th/0601001`) vs new (`2402.03300`)
 - PDF: `https://arxiv.org/pdf/{id}` — Abstract: `https://arxiv.org/abs/{id}`
 - HTML (when available): `https://arxiv.org/html/{id}`
diff --git a/skills/research/grounded-citations/SKILL.md b/skills/research/grounded-citations/SKILL.md
index fe703d1df9edc..4c767369f4d97 100644
--- a/skills/research/grounded-citations/SKILL.md
+++ b/skills/research/grounded-citations/SKILL.md
@@ -58,12 +58,12 @@ Override per task with `--ledger <path>` or `HERMES_CITATION_LEDGER`.
 ```bash
 S=~/.hermes/skills/research/grounded-citations/scripts/sources.py
 
-python3 "$S" reset                                  # start a clean ledger
-python3 "$S" add https://example.com/a --title "A"  # prints: [1]
-python3 "$S" add https://example.com/b --title "B"  # prints: [2]
-python3 "$S" list                                   # ledger table
-python3 "$S" render                                 # Sources: block
-python3 "$S" verify draft.md                        # catch bad citations
+python "$S" reset                                  # start a clean ledger
+python "$S" add https://example.com/a --title "A"  # prints: [1]
+python "$S" add https://example.com/b --title "B"  # prints: [2]
+python "$S" list                                   # ledger table
+python "$S" render                                 # Sources: block
+python "$S" verify draft.md                        # catch bad citations
 ```
 
 `add` is idempotent and URL-normalized: the same page always returns the same
@@ -136,7 +136,7 @@ upgrade from citations to evidence:
 text to a file and attach the sentence(s) that carry each claim:
 
 ```bash
-python3 "$S" quote 1 --text "Ice is about 9% less dense than liquid water." --from page1.txt
+python "$S" quote 1 --text "Ice is about 9% less dense than liquid water." --from page1.txt
 ```
 
 The quote is rejected unless it appears verbatim in the evidence text
@@ -168,8 +168,8 @@ corroboration.
 ④ **Verify with the evidence gate and render the evidence block:**
 
 ```bash
-python3 "$S" verify report.md --evidence --min-coverage 0.5
-python3 "$S" render --style evidence --replace-in report.md
+python "$S" verify report.md --evidence --min-coverage 0.5
+python "$S" render --style evidence --replace-in report.md
 ```
 
 `--evidence` fails the draft if any cited source has no attached quote. The
@@ -222,7 +222,7 @@ and read the `info: stats:` line to see the counts before picking a number.
 ## Verification
 
 ```bash
-python3 "$S" verify report.md --strict --min-coverage 0.5
+python "$S" verify report.md --strict --min-coverage 0.5
 ```
 
 Green means: every `[n]` in the draft exists in the ledger, the Sources block
diff --git a/skills/software-development/hermes-agent-skill-authoring/SKILL.md b/skills/software-development/hermes-agent-skill-authoring/SKILL.md
index b51120514ae55..c199a0c5897ae 100644
--- a/skills/software-development/hermes-agent-skill-authoring/SKILL.md
+++ b/skills/software-development/hermes-agent-skill-authoring/SKILL.md
@@ -148,7 +148,7 @@ A skill exists to make the agent's process more predictable — the agent reliab
 ## Tests and Docs (required for repo skills)
 
 1. **Tests** live at `tests/skills/test_<skill>_skill.py` — stdlib + pytest + `unittest.mock` only, no live network. Run via `scripts/run_tests.sh tests/skills/test_<skill>_skill.py -q`. (The generic `tests/tools/test_skill_manager_tool.py` passing proves nothing about YOUR skill.)
-2. **Docs regen:** run `python3 website/scripts/generate-skill-docs.py`, then apply scope discipline — the generator rewrites EVERY auto-gen page. `git checkout --` everything that isn't yours; the final diff must show only your SKILL.md, your one per-skill docs page, a one-line catalog row, and a one-line `website/sidebars.ts` insertion (verify with `search_files(pattern='<your-slug>', path='website/sidebars.ts')` — exactly one hit, or the page is an orphan).
+2. **Docs regen:** run `python website/scripts/generate-skill-docs.py`, then apply scope discipline — the generator rewrites EVERY auto-gen page. `git checkout --` everything that isn't yours; the final diff must show only your SKILL.md, your one per-skill docs page, a one-line catalog row, and a one-line `website/sidebars.ts` insertion (verify with `search_files(pattern='<your-slug>', path='website/sidebars.ts')` — exactly one hit, or the page is an orphan).
 3. **`.env.example`** (only if the skill needs new env vars): one clearly delimited commented block; touch nothing else in the file.
 
 ## Workflow
diff --git a/skills/software-development/spike/SKILL.md b/skills/software-development/spike/SKILL.md
index 2a980f0ade952..94ca054dd2fa5 100644
--- a/skills/software-development/spike/SKILL.md
+++ b/skills/software-development/spike/SKILL.md
@@ -118,7 +118,7 @@ spikes/
 terminal("mkdir -p spikes/001-websocket-streaming")
 write_file("spikes/001-websocket-streaming/README.md", "# 001: websocket-streaming\n\n...")
 write_file("spikes/001-websocket-streaming/main.py", "...")
-terminal("cd spikes/001-websocket-streaming && python3 main.py")
+terminal("cd spikes/001-websocket-streaming && python main.py")
 # Observe output, iterate.
 ```
 
diff --git a/tools/mcp_tool.py b/tools/mcp_tool.py
index 88f02f6f4d7cb..f380b8cea4ff3 100644
--- a/tools/mcp_tool.py
+++ b/tools/mcp_tool.py
@@ -794,6 +794,27 @@ def _resolve_stdio_command(command: str, env: dict) -> tuple[str, dict]:
     if os.sep not in resolved_command:
         path_arg = resolved_env["PATH"] if "PATH" in resolved_env else None
         which_hit = shutil.which(resolved_command, path=path_arg)
+        if which_hit is None and sys.platform == "win32" and resolved_env:
+            # shutil.which(..., path=...) resolves extensions from the PARENT
+            # process PATHEXT, not the MCP subprocess env — so a config that
+            # supplies both PATH and PATHEXT can fail to resolve a command
+            # its own env can find (#56536). Retry with the config's PATHEXT
+            # (any key casing: PATHEXT / Pathext / pathext) applied.
+            cfg_pathext = next(
+                (v for k, v in resolved_env.items()
+                 if k.upper() == "PATHEXT" and isinstance(v, str) and v.strip()),
+                None,
+            )
+            if cfg_pathext and cfg_pathext != os.environ.get("PATHEXT"):
+                _saved = os.environ.get("PATHEXT")
+                try:
+                    os.environ["PATHEXT"] = cfg_pathext
+                    which_hit = shutil.which(resolved_command, path=path_arg)
+                finally:
+                    if _saved is None:
+                        os.environ.pop("PATHEXT", None)
+                    else:
+                        os.environ["PATHEXT"] = _saved
         if which_hit:
             resolved_command = which_hit
         elif resolved_command in {"npx", "npm", "node"}: