diff --git a/SKILL.md b/SKILL.md index 222b6922c..c12abf895 100644 --- a/SKILL.md +++ b/SKILL.md @@ -109,7 +109,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/autoplan/SKILL.md b/autoplan/SKILL.md index 21680d6dd..7125aa255 100644 --- a/autoplan/SKILL.md +++ b/autoplan/SKILL.md @@ -119,7 +119,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/benchmark/SKILL.md b/benchmark/SKILL.md index a21c1fd40..a49b542cc 100644 --- a/benchmark/SKILL.md +++ b/benchmark/SKILL.md @@ -112,7 +112,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/browse/SKILL.md b/browse/SKILL.md index b5aed0dcb..c586b2542 100644 --- a/browse/SKILL.md +++ b/browse/SKILL.md @@ -111,7 +111,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/canary/SKILL.md b/canary/SKILL.md index 70d36b239..618a7308b 100644 --- a/canary/SKILL.md +++ b/canary/SKILL.md @@ -111,7 +111,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/checkpoint/SKILL.md b/checkpoint/SKILL.md index 7580ebbc2..88d5b9fb4 100644 --- a/checkpoint/SKILL.md +++ b/checkpoint/SKILL.md @@ -114,7 +114,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/codex/SKILL.md b/codex/SKILL.md index 1cd9f3ac6..5ecaecfdb 100644 --- a/codex/SKILL.md +++ b/codex/SKILL.md @@ -113,7 +113,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/cso/SKILL.md b/cso/SKILL.md index 798210183..501f8eea9 100644 --- a/cso/SKILL.md +++ b/cso/SKILL.md @@ -116,7 +116,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/design-consultation/SKILL.md b/design-consultation/SKILL.md index 2f4623354..939c1a364 100644 --- a/design-consultation/SKILL.md +++ b/design-consultation/SKILL.md @@ -116,7 +116,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/design-html/SKILL.md b/design-html/SKILL.md index 4cb8ef5f6..f51af367b 100644 --- a/design-html/SKILL.md +++ b/design-html/SKILL.md @@ -118,7 +118,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/design-review/SKILL.md b/design-review/SKILL.md index fa77d86b1..c92d5d81e 100644 --- a/design-review/SKILL.md +++ b/design-review/SKILL.md @@ -116,7 +116,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/design-shotgun/SKILL.md b/design-shotgun/SKILL.md index fce1b5233..7154f0861 100644 --- a/design-shotgun/SKILL.md +++ b/design-shotgun/SKILL.md @@ -113,7 +113,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/devex-review/SKILL.md b/devex-review/SKILL.md index f875affa4..2d297d15e 100644 --- a/devex-review/SKILL.md +++ b/devex-review/SKILL.md @@ -116,7 +116,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/document-release/SKILL.md b/document-release/SKILL.md index 6a9b1ee3c..ee2829567 100644 --- a/document-release/SKILL.md +++ b/document-release/SKILL.md @@ -113,7 +113,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/health/SKILL.md b/health/SKILL.md index 1dc91ef70..9e2bddb5c 100644 --- a/health/SKILL.md +++ b/health/SKILL.md @@ -113,7 +113,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/investigate/SKILL.md b/investigate/SKILL.md index 6945d1825..7321e586f 100644 --- a/investigate/SKILL.md +++ b/investigate/SKILL.md @@ -128,7 +128,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/land-and-deploy/SKILL.md b/land-and-deploy/SKILL.md index 1382cd4bc..4f440fb5f 100644 --- a/land-and-deploy/SKILL.md +++ b/land-and-deploy/SKILL.md @@ -110,7 +110,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/learn/SKILL.md b/learn/SKILL.md index daac2c50d..7ac09a94d 100644 --- a/learn/SKILL.md +++ b/learn/SKILL.md @@ -113,7 +113,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/office-hours/SKILL.md b/office-hours/SKILL.md index e4fcdf7c4..1b949b34b 100644 --- a/office-hours/SKILL.md +++ b/office-hours/SKILL.md @@ -120,7 +120,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/open-gstack-browser/SKILL.md b/open-gstack-browser/SKILL.md index 18b463bd9..55836072a 100644 --- a/open-gstack-browser/SKILL.md +++ b/open-gstack-browser/SKILL.md @@ -110,7 +110,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/pair-agent/SKILL.md b/pair-agent/SKILL.md index ae91d526c..d18a2d4d6 100644 --- a/pair-agent/SKILL.md +++ b/pair-agent/SKILL.md @@ -111,7 +111,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/plan-ceo-review/SKILL.md b/plan-ceo-review/SKILL.md index 9ee5bffac..1cab02682 100644 --- a/plan-ceo-review/SKILL.md +++ b/plan-ceo-review/SKILL.md @@ -116,7 +116,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/plan-design-review/SKILL.md b/plan-design-review/SKILL.md index 880c04d94..c08e8d510 100644 --- a/plan-design-review/SKILL.md +++ b/plan-design-review/SKILL.md @@ -114,7 +114,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/plan-devex-review/SKILL.md b/plan-devex-review/SKILL.md index 9e050c7ee..c9bc991f5 100644 --- a/plan-devex-review/SKILL.md +++ b/plan-devex-review/SKILL.md @@ -118,7 +118,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/plan-eng-review/SKILL.md b/plan-eng-review/SKILL.md index f767af0ee..4d097beaf 100644 --- a/plan-eng-review/SKILL.md +++ b/plan-eng-review/SKILL.md @@ -116,7 +116,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/qa-only/SKILL.md b/qa-only/SKILL.md index 2df6552ff..6de9449b5 100644 --- a/qa-only/SKILL.md +++ b/qa-only/SKILL.md @@ -112,7 +112,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/qa/SKILL.md b/qa/SKILL.md index ed101d0b8..3f41b78e6 100644 --- a/qa/SKILL.md +++ b/qa/SKILL.md @@ -118,7 +118,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/retro/SKILL.md b/retro/SKILL.md index 9cbdbc38a..a819a4dfc 100644 --- a/retro/SKILL.md +++ b/retro/SKILL.md @@ -111,7 +111,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/review/SKILL.md b/review/SKILL.md index 4c0880cf2..52446c316 100644 --- a/review/SKILL.md +++ b/review/SKILL.md @@ -114,7 +114,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/scripts/resolvers/preamble.ts b/scripts/resolvers/preamble.ts index 22dce24c5..da68656c0 100644 --- a/scripts/resolvers/preamble.ts +++ b/scripts/resolvers/preamble.ts @@ -121,7 +121,38 @@ or invoking other gstack skills, use the \`/gstack-\` prefix (e.g., \`/gstack-qa of \`/qa\`, \`/gstack-ship\` instead of \`/ship\`). Disk paths are unaffected — always use \`${ctx.paths.skillRoot}/[skill-name]/SKILL.md\` for reading skill files. -If output shows \`UPGRADE_AVAILABLE \`: read \`${ctx.paths.skillRoot}/gstack-upgrade/SKILL.md\` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If \`JUST_UPGRADED \`: tell user "Running gstack v{to} (just updated!)" and continue.`; +If output shows \`UPGRADE_AVAILABLE \`: read \`${ctx.paths.skillRoot}/gstack-upgrade/SKILL.md\` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows \`JUST_UPGRADED \` AND \`SPAWNED_SESSION\` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (\`SPAWNED_SESSION\` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. \`${ctx.paths.skillRoot}/.feature-prompted-continuous-checkpoint\` → + Prompt: "Continuous checkpoint auto-commits your work as you go with \`WIP:\` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run \`${ctx.paths.binDir}/gstack-config set checkpoint_mode continuous\`. + Always: \`touch ${ctx.paths.skillRoot}/.feature-prompted-continuous-checkpoint\` + +2. \`${ctx.paths.skillRoot}/.feature-prompted-model-overlay\` → + Inform only (no prompt): "Model overlays are active. \`MODEL_OVERLAY: {model}\` + shown in the preamble output tells you which behavioral patch is applied. + Override with \`--model\` when regenerating skills (e.g., \`bun run gen:skill-docs + --model gpt-5.4\`). Default is claude." + Always: \`touch ${ctx.paths.skillRoot}/.feature-prompted-model-overlay\` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow.`; } function generateLakeIntro(): string { diff --git a/setup-browser-cookies/SKILL.md b/setup-browser-cookies/SKILL.md index a7952fc29..1d41a54d1 100644 --- a/setup-browser-cookies/SKILL.md +++ b/setup-browser-cookies/SKILL.md @@ -108,7 +108,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/setup-deploy/SKILL.md b/setup-deploy/SKILL.md index 02940019b..87cc6a30a 100644 --- a/setup-deploy/SKILL.md +++ b/setup-deploy/SKILL.md @@ -114,7 +114,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/ship/SKILL.md b/ship/SKILL.md index df977d84c..b9e6e4418 100644 --- a/ship/SKILL.md +++ b/ship/SKILL.md @@ -115,7 +115,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/test/fixtures/golden/claude-ship-SKILL.md b/test/fixtures/golden/claude-ship-SKILL.md index df977d84c..b9e6e4418 100644 --- a/test/fixtures/golden/claude-ship-SKILL.md +++ b/test/fixtures/golden/claude-ship-SKILL.md @@ -115,7 +115,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `~/.claude/skills/gstack/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. + Always: `touch ~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint` + +2. `~/.claude/skills/gstack/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch ~/.claude/skills/gstack/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/test/fixtures/golden/codex-ship-SKILL.md b/test/fixtures/golden/codex-ship-SKILL.md index 9599ecdac..04c4c050e 100644 --- a/test/fixtures/golden/codex-ship-SKILL.md +++ b/test/fixtures/golden/codex-ship-SKILL.md @@ -109,7 +109,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `$GSTACK_ROOT/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `$GSTACK_ROOT/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `$GSTACK_ROOT/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `$GSTACK_ROOT/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `$GSTACK_BIN/gstack-config set checkpoint_mode continuous`. + Always: `touch $GSTACK_ROOT/.feature-prompted-continuous-checkpoint` + +2. `$GSTACK_ROOT/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch $GSTACK_ROOT/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete diff --git a/test/fixtures/golden/factory-ship-SKILL.md b/test/fixtures/golden/factory-ship-SKILL.md index e42377a60..0aa5b4a28 100644 --- a/test/fixtures/golden/factory-ship-SKILL.md +++ b/test/fixtures/golden/factory-ship-SKILL.md @@ -111,7 +111,38 @@ or invoking other gstack skills, use the `/gstack-` prefix (e.g., `/gstack-qa` i of `/qa`, `/gstack-ship` instead of `/ship`). Disk paths are unaffected — always use `$GSTACK_ROOT/[skill-name]/SKILL.md` for reading skill files. -If output shows `UPGRADE_AVAILABLE `: read `$GSTACK_ROOT/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If `JUST_UPGRADED `: tell user "Running gstack v{to} (just updated!)" and continue. +If output shows `UPGRADE_AVAILABLE `: read `$GSTACK_ROOT/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). + +If output shows `JUST_UPGRADED ` AND `SPAWNED_SESSION` is NOT set: tell +the user "Running gstack v{to} (just updated!)" and then check for new features to +surface. For each per-feature marker below, if the marker file is missing AND the +feature is plausibly useful for this user, use AskUserQuestion to let them try it. +Fire once per feature per user, NOT once per upgrade. + +**In spawned sessions (`SPAWNED_SESSION` = "true"): SKIP feature discovery entirely.** +Just print "Running gstack v{to}" and continue. Orchestrators do not want interactive +prompts from sub-sessions. + +**Feature discovery markers and prompts** (one at a time, max one per session): + +1. `$GSTACK_ROOT/.feature-prompted-continuous-checkpoint` → + Prompt: "Continuous checkpoint auto-commits your work as you go with `WIP:` prefix + so you never lose progress to a crash. Local-only by default — doesn't push + anywhere unless you turn that on. Want to try it?" + Options: A) Enable continuous mode, B) Show me first (print the section from + the preamble Continuous Checkpoint Mode), C) Skip. + If A: run `$GSTACK_BIN/gstack-config set checkpoint_mode continuous`. + Always: `touch $GSTACK_ROOT/.feature-prompted-continuous-checkpoint` + +2. `$GSTACK_ROOT/.feature-prompted-model-overlay` → + Inform only (no prompt): "Model overlays are active. `MODEL_OVERLAY: {model}` + shown in the preamble output tells you which behavioral patch is applied. + Override with `--model` when regenerating skills (e.g., `bun run gen:skill-docs + --model gpt-5.4`). Default is claude." + Always: `touch $GSTACK_ROOT/.feature-prompted-model-overlay` + +After handling JUST_UPGRADED (prompts done or skipped), continue with the skill +workflow. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle. Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete