agentleFS
AI-Driven-SchoolAI-Driven-School/aiki/.claude/skills/project/SKILL.md

project

Skill0 starsChanged 9 months agoMITView on GitHub

Run the full design-to-deploy pipeline using 3 AIs (Claude + Codex + Gemini). Use when starting a new feature, running /project, or needing end-to-end development with requirements, specs, implementation, testing, review, and deployment phases.

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ingest, next and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 5 projects that use this

  • VercelSkill

    next

    Next.js renderer for json-render that turns JSON specs into full Next.js applications with routes, layouts, SSR, and metadata. Use when working with @json-render/next, building Next.js apps from JSON specs, or creating AI-generated multi-page applications.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    lint

    Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.

    Also in 4 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 8 projects that use this

  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 5 projects that use this

  • GoogleSkill

    teach

    Teach the user a new skill or concept, within this workspace.

    Also in 4 projects that use this

The file

Files
SKILL.md

/project スキル

機能名を指定すると、要件定義から実装・テスト・デプロイまで6フェーズで自動実行します。

使用方法

/project ユーザー認証
/project 商品検索機能
/project ダッシュボード

実行フロー

[1/6] 要件定義   (Claude)  → docs/requirements/{feature}.md
[2/6] 設計       (Claude)  → docs/specs/{feature}.md, docs/api/{feature}.yaml
[3/6] 実装       (Codex)   → src/**/*
[4/6] テスト     (Codex)   → tests/**/*
[5/6] レビュー   (Claude)  → docs/reviews/{feature}.md
[6/6] デプロイ   (Claude)  → 最終確認

フェーズ詳細

Phase 1: 要件定義(Claude)

以下のテンプレートで要件定義書を生成:

# 要件定義: {機能名}

## ユーザーストーリー

AS A {ユーザー種別}
I WANT TO {やりたいこと}
SO THAT {達成したい目的}

## 受入条件

### 機能要件
- [ ] {条件1}
- [ ] {条件2}
- [ ] {条件3}

### 非機能要件
- パフォーマンス: {要件}
- セキュリティ: {要件}
- アクセシビリティ: {要件}

## 制約事項
- フレームワーク: {使用技術}
- データ永続化: {方式}

出力先: docs/requirements/{feature}.md 承認: ユーザーに確認 → Y で次へ、reject {理由} で再生成

Phase 2: 設計(Claude)

画面設計

# 画面設計: {画面名}

## 概要
{画面の目的と概要}

## コンポーネント構成
| コンポーネント | 種類 | 説明 |
|--------------|------|------|
| {名前} | {種類} | {説明} |

## 状態遷移
| 状態 | トリガー | 遷移先 |
|------|---------|--------|
| {状態} | {操作} | {次の状態} |

## インタラクション
- {操作}: {動作}

API設計(OpenAPI形式)

openapi: 3.0.0
info:
  title: {機能名} API
  version: 1.0.0
paths:
  /{endpoint}:
    post:
      summary: {概要}
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                {field}:
                  type: {type}
      responses:
        '200':
          description: 成功

出力先: docs/specs/{feature}.md, docs/api/{feature}.yaml 承認: ユーザーに確認

Phase 3: 実装(Codex)

設計書を基にCodexで実装を委譲:

# Codexに委譲
codex exec "
以下の設計書を読み込み、実装してください:
- docs/requirements/{feature}.md
- docs/specs/{feature}.md
- docs/api/{feature}.yaml

実装要件:
- Next.js App Router
- TypeScript
- Tailwind CSS
- 既存のコードスタイルに従う
" --full-auto

出力先: src/ 配下 自動実行: 承認不要(full-auto)

Phase 4: テスト(Codex)

# Codexに委譲
codex exec "
実装したコードに対してテストを生成してください:
- E2Eテスト(Playwright)
- 受入条件を全てカバー
" --full-auto

出力先: tests/{feature}.spec.ts 自動実行: 承認不要

Phase 5: レビュー(Claude)

実装コードを設計書と照合し、レビュー:

# コードレビュー: {機能名}

## サマリー
- 受入条件: {N}/{M} クリア
- テストカバレッジ: {X}%
- 改善提案: {N}件

## チェック結果

### 受入条件
- [x] {条件1}
- [x] {条件2}
- [ ] {条件3} → {理由}

### セキュリティ
- {チェック項目}: {結果}

### 改善提案
1. {提案1}
2. {提案2}

出力先: docs/reviews/{feature}.md

Phase 6: デプロイ(Claude)

レビュー結果を確認し、デプロイ判断:

レビュー結果:
  ✅ 受入条件クリア
  ✅ テストパス
  ⚠️ 軽微な改善提案あり(デプロイに影響なし)

本番にデプロイしますか? [Y/n]

デプロイ承認後:

# Vercelデプロイ
vercel --prod

中断・再開

# 進捗確認
/status

# 特定フェーズから再開
/project {機能名} --from=3

# フェーズスキップ
/project {機能名} --skip=1,2

出力例

> /project ユーザー認証

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🚀 プロジェクト開始: ユーザー認証
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

[1/6] 要件定義を生成中... (Claude)
      → docs/requirements/auth.md

📄 要件定義:
───────────────────────────────
# 要件定義: ユーザー認証

## ユーザーストーリー
AS A 一般ユーザー
I WANT TO アカウントでログインしたい
SO THAT 個人データにアクセスできる
...
───────────────────────────────

承認しますか? [Y/n/reject 理由] > Y
✓ 要件定義を承認しました

[2/6] 設計を生成中... (Claude)
      → docs/specs/auth.md
      → docs/api/auth.yaml
...

[3/6] 実装中... (Codex - full-auto) ★
      → src/app/login/page.tsx
      → src/app/api/auth/login/route.ts
      → src/lib/auth.ts

[4/6] テスト生成中... (Codex)
      → tests/auth.spec.ts

[5/6] レビュー中... (Claude)
      ✓ 受入条件: 5/5 クリア
      ✓ テスト: 6 passed
      ⚠️ 改善提案: 2件

[6/6] デプロイ準備完了
      本番にデプロイしますか? [Y/n] > Y

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ デプロイ完了!
   URL: https://my-app.vercel.app
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.