Install
$ agentstack add skill-jonayeon-claude-code-skills-work-ai-project-archetype-selector ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Project Archetype Selector: {{title}}
1. This Project Feels Most Like
프로젝트의 성격을 아키타입으로 분류합니다. 복수 선택 가능.
- Primary archetype:
- Secondary archetype:
- Why these fit:
아키타입 목록: | 아키타입 | 설명 | 대표적 반복 작업 | |----------|------|------------------| | Web App (Full-stack) | 프론트+백엔드 웹 서비스 | 컴포넌트 생성, API 연동, DB 마이그레이션 | | API Service | REST/GraphQL API 서버 | 엔드포인트 추가, 스키마 변경, 인증 처리 | | Data Pipeline | ETL, 배치, 데이터 처리 | 파이프라인 추가, 스키마 변환, 모니터링 | | CLI Tool | 터미널 도구, 스크립트 | 커맨드 추가, 옵션 파싱, 출력 포맷팅 | | Library / SDK | 재사용 패키지 | API 설계, 테스트, 문서화, 버전 관리 | | Mobile App | iOS/Android/Flutter 등 | 화면 추가, 네비게이션, 상태관리 | | Infra / DevOps | IaC, CI/CD, 모니터링 | 리소스 프로비저닝, 파이프라인 수정 | | ML / AI | 모델 학습, 추론 서비스 | 실험 추적, 데이터 전처리, 모델 배포 | | Content / Docs | 문서화, 블로그, 지식관리 | 문서 작성, 템플릿 관리, 검수 |
Reference:
- [[Project Archetype Skill Map]]
2. Project Snapshot
> 이 섹션의 값은 [[00_Project Context]] 에서 가져온다.
- Project:
- Goal:
- Repo / folder:
- Stage:
- Main deliverable:
3. Real Repeated Tasks
직접 경험한 반복 작업을 구체적으로 적습니다. 이것이 스킬 선택의 핵심 근거입니다.
- What do I keep doing?
-
- What is slow or annoying?
-
- What do I want the model to do better?
-
4. Constraints
프로젝트의 기술적·환경적 제약을 기록합니다. 스킬 호환성 판단에 사용됩니다.
- Stack:
- Tools already in use:
- Risky actions to avoid:
- Credentials / external systems:
- Time budget:
5. What I Want Recommended
- Number of skill candidates:
- Prefer official / community / mixed:
- Okay to suggest local custom skill?:
- Exclude anything?:
6. Paste Prompt
Use this note and [[Project Archetype Skill Map]] as the context for skill selection.
First identify the project's primary and secondary archetypes.
Then inspect the codebase or working docs and recommend only the smallest useful shortlist.
Requirements:
- Prefer official / high-trust skills first
- Keep the shortlist small (3-5 candidates max)
- Separate: install now / optional later / skip or risky
- Explain why each recommendation matches this project's repeated tasks
- If no strong fit exists, suggest a small local custom skill instead
- Consider the constraints listed in section 4
Keep the answer practical and concise.
7. Skill Selection Log
선택 결과를 기록합니다.
| Skill | Why it matched | Decision | Notes | |---|---|---|---| | | | candidate / adopted / skipped | | | | | | | | | | | |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: JoNaYeon
- Source: JoNaYeon/claude-code-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.