RomanNum3ral
/
gstack
mirror of https://github.com/garrytan/gstack.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs: add /plan-design-review to demo, tighten CEO response 

Shorter CEO reply, compressed eng diagram, added design audit with
AI Slop score. Seven commands now: plan → eng → build → design →
review → QA → ship.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-03-17 14:02:23 -07:00
parent 185b588c74
commit 11842a501a
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
1 changed files with 16 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
README.md
View File

@ -29,51 +29,45 @@ Fork it. Improve it. Make it yours. Don't player hate, appreciate.
``` ```
You: I want to add photo upload for sellers. You: I want to add photo upload for sellers.
You: /plan-ceo-review You: /plan-ceo-review
Claude: "Photo upload" is not the feature. The real job is helping Claude: "Photo upload" is not the feature. The real job is helping
sellers create listings that actually sell. sellers create listings that actually sell. What if we
auto-identify the product, pull specs and comps from the
What if we auto-identify the product from the photo, pull web, and draft the listing automatically? That's 10 stars.
specs and pricing comps from the web, draft the title and "Upload a photo" is 3 stars. Which are we building?
description, and suggest the best hero image?
That's a 10-star listing experience. "Upload a photo" is
a 3-star one. Which are we building?
You: /plan-eng-review You: /plan-eng-review
Claude: ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌─────────┐ Claude: ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌─────────┐
│ Upload │───▶│ Classify │───▶│ Enrich │───▶│ Draft │ │ Upload │───▶│ Classify │───▶│ Enrich │───▶│ Draft │
│ (sync) │ │ (async) │ │ (async) │ │ (async) │ │ (sync) │ │ (async) │ │ (async) │ │ (async) │
└─────────┘ └──────────┘ └──────────┘ └─────────┘ └─────────┘ └──────────┘ └──────────┘ └─────────┘
│ │ │ │
▼ ▼ ▼ ▼
S3 + DB Vision API WebSearch + LLM gen +
persist + fallback price APIs user edit
Failure modes: 6 mapped. Test matrix: 14 cases. Failure modes: 6 mapped. Test matrix: 14 cases.
Missing: what if classify returns low-confidence?
You: Approve plan. Exit plan mode. You: Approve plan. Exit plan mode.
[Claude implements the feature] [Claude implements the feature]
You: /plan-design-review https://staging.myapp.com
Claude: Design Score: B | AI Slop Score: C
"Upload flow looks like a default Bootstrap form."
Top fix: custom drag-drop zone with preview grid.
You: /review You: /review
Claude: [AUTO-FIXED] Orphan S3 cleanup on failed upload Claude: [AUTO-FIXED] Orphan S3 cleanup on failed upload
[AUTO-FIXED] Missing index on listings.status [AUTO-FIXED] Missing index on listings.status
[ASK] Race condition: two tabs can overwrite hero image [ASK] Race condition on hero image selection → You: yes
selection. Add SELECT FOR UPDATE? → You: yes 3 issues — 2 auto-fixed, 1 fixed.
Pre-Landing Review: 3 issues — 2 auto-fixed, 1 fixed.
You: /qa https://staging.myapp.com You: /qa https://staging.myapp.com
Claude: Upload → classify → enrich → draft: end to end ✓ Claude: Upload → classify → enrich → draft: end to end ✓
Mobile upload: ✓ | Slow connection: ✓ | Bad image: ✓ Mobile: ✓ | Slow connection: ✓ | Bad image: ✓
Regression test generated: test/qa-regression-001.test.ts Regression test generated.
You: /ship You: /ship
Claude: Tests: 42 → 51 (+9 new) Claude: Tests: 42 → 51 (+9 new)
Coverage: 14/14 code paths tested (100%) Coverage: 14/14 code paths (100%)
PR: github.com/you/app/pull/42 PR: github.com/you/app/pull/42
``` ```
One feature. Six commands. CEO taste → architecture → review → QA → ship. The agent found a race condition I would have missed, auto-fixed two issues I didn't even think about, wrote 9 tests, and generated a regression test from QA. That is not a copilot. That is a team. One feature. Seven commands. CEO taste → architecture → build → design audit → review → QA → ship. The agent reframed the product, found a race condition I would have missed, auto-fixed two issues, caught the AI slop in my UI, wrote 9 tests, and generated a regression test. That is not a copilot. That is a team.
--- ---