adversarial-coach
killerapp 제작
Personal Development요약
Adversarial implementation review based on Block's g3.
설명
이 스킬이 하는 일
A dialectical review loop where an adversarial coach independently validates implementation completeness against a requirements file. Based on Block's g3 research, it separates the implementing agent from the reviewer to catch gaps the implementer would rationalize away. Returns either IMPLEMENTATION_APPROVED or a concrete list of missing items.
Unlike self-review, the coach discards prior context and evaluates code against requirements as written, catching gaps the implementing agent would overlook or excuse.
사용 시점
- Catching missing auth endpoints before code review
- Verifying a spec is fully implemented after a coding session
- Looping on fixes until all requirements are met
- Reviewing JWT/bcrypt security gaps in auth implementations
- Validating edge case test coverage against a written spec
예시 워크플로
User asks: /coach SPEC.md
- 1
Locate and parse SPEC.md to extract all requirements
- 2
Review the current implementation independently, ignoring prior conversation context
- 3
Check each requirement for implementation status, compilation, tests, and security gaps
- 4
Return compliance report with IMMEDIATE ACTIONS NEEDED listing specific files and fixes
- 5
After user applies fixes, re-run review until IMPLEMENTATION_APPROVED is issued
IMPLEMENTATION_APPROVED with each requirement verified and test count confirmed
설치
clawhub install killerapp/adversarial-coachCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.