agentleFS
ilhae-aiilhae-ai/claude-code-orchestrator/.claude/skills/startproject/SKILL.md

startproject

Skill18 starsChanged 10 months agoMITView on GitHub

Start a new project/feature implementation with multi-agent collaboration. Includes multi-session review workflow for quality assurance.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. gaebalai/claude-code-orchestrator★ 18100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository13 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use TodoWrite to create tasks:

    line 118
  2. Distinctive:

    Start new Claude Code session

    line 164
  3. Distinctive:

    Run: git diff main...HEAD to see all changes

    line 165
  4. Distinctive:

    Ask Claude to review the implementation

    line 166

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Start Project

멀티 에이전트 협업으로 프로젝트를 시작한다.

Overview

이 스킬은 3개의 에이전트(Claude, Codex, Gemini)를 협조시켜 프로젝트 개시부터 구현후 리뷰까지를 커버한다.

Workflow

Phase 1: Research (Gemini via Subagent)
    ↓
Phase 2: Requirements & Planning (Claude)
    ↓
Phase 3: Design Review (Codex via Subagent)
    ↓
Phase 4: Task Creation (Claude)
    ↓
Phase 5: CLAUDE.md Update (Claude)
    ↓
[Implementation...]
    ↓
Phase 6: Multi-Session Review (New Session + Codex)

Phase 1: Gemini Research (Background)

Task tool에서 하위 에이전트를 시작하고 Gemini에서 리포지토리 분석한다.

Task tool parameters:
- subagent_type: "general-purpose"
- run_in_background: true
- prompt: |
    Research for: {feature}

    1. Call Gemini CLI:
       gemini -p "Analyze this repository for: {feature}

       Provide:
       1. Repository structure and architecture
       2. Relevant existing code and patterns
       3. Library recommendations
       4. Technical considerations
       " --include-directories . 2>/dev/null

    2. Save full output to: .claude/docs/research/{feature}.md

    3. Return CONCISE summary (5-7 bullet points)

Phase 2: Requirements Gathering (Claude)

사용자에게 질문하여 요구 사항을 명확히 한다.

Ask in Korean:

  1. 목적: 무엇을 달성하고 싶습니까?
  2. 스코프: 포함하거나 제외하는 것은?
  3. 기술적 요건: 특정 라이브러리, 제약은?
  4. 성공기준: 완료의 판단기준은?

Draft implementation plan based on Gemini research + user answers.


Phase 3: Codex Design Review (Background)

Task tool에서 하위 에이전트를 시작하고 Codex에서 계획 검토한다.

Task tool parameters:
- subagent_type: "general-purpose"
- run_in_background: true
- prompt: |
    Review plan for: {feature}

    Draft plan: {plan from Phase 2}

    1. Call Codex CLI:
       codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "
       Review this implementation plan:
       {plan}

       Analyze:
       1. Approach assessment
       2. Risk analysis
       3. Implementation order
       4. Improvements
       " 2>/dev/null

    2. Return CONCISE summary:
       - Top 3-5 recommendations
       - Key risks
       - Suggested order

Phase 4: Task Creation (Claude)

서브에이전트 요약을 통합하고 작업 목록을 작성한다.

Use TodoWrite to create tasks:

{
    "content": "Implement {specific feature}",
    "activeForm": "Implementing {specific feature}",
    "status": "pending"
}

Phase 5: CLAUDE.md Update (IMPORTANT)

프로젝트 관련 정보를 CLAUDE.md에 추가한다.

Add to CLAUDE.md:

---

## Current Project: {feature}

### Context
- Goal: {1-2 sentences}
- Key files: {list}
- Dependencies: {list}

### Decisions
- {Decision 1}: {rationale}
- {Decision 2}: {rationale}

### Notes
- {Important constraints or considerations}

This ensures context persists across sessions.


Phase 6: Multi-Session Review (Post-Implementation)

구현 완료 후 다른 세션에서 리뷰를 실시한다.

Option A: New Claude Session

  1. Start new Claude Code session
  2. Run: git diff main...HEAD to see all changes
  3. Ask Claude to review the implementation

Option B: Codex Review (via Subagent)

Task tool parameters:
- subagent_type: "general-purpose"
- prompt: |
    Review implementation for: {feature}

    1. Run: git diff main...HEAD
    2. Call Codex CLI:
       codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "
       Review this implementation:
       {diff output}

       Check:
       1. Code quality and patterns
       2. Potential bugs
       3. Missing edge cases
       4. Security concerns
       " 2>/dev/null

    3. Return findings and recommendations

Why Multi-Session Review?

  • Fresh perspective: New session has no bias from implementation
  • Different context: Can focus purely on review, not implementation details
  • Codex strength: Deep analysis without context pollution

User Confirmation

Present final plan to user (in Korean):

## 프로젝트 계획 : {feature}

### 조사 결과 (Gemini)
{Key findings - 3-5 bullet points}

### 설계 정책 (Codex 검토)
{Approach with refinements}

### 작업 목록 ({N}개)
{Task list}

### 위험과 주의사항
{From Codex analysis}

### 다음 단계
1. 이 계획으로 진행하시겠습니까?
2. 구현 완료 후 다른 세션에서 검토를 수행한다.

---
이 계획으로 진행하시겠습니까?

Output Files

FilePurpose
.claude/docs/research/{feature}.mdGemini research output
CLAUDE.mdUpdated with project context
Task list (internal)Progress tracking

Tips

  • All Codex/Gemini work through subagents to preserve main context
  • Update CLAUDE.md to persist context across sessions
  • Use multi-session review for better quality assurance
  • Ctrl+T: Toggle task list visibility

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.