·roast-my-agents-md
</>

roast-my-agents-md

✓
vltansky/roast-my-agents-mdGitHub: vltansky/roast-my-agents-md출처: vltansky/roast-my-agents-md

Brutally honest AGENTS.md/CLAUDE.md review backed by real A/B test evidence. Not just opinions — actual proof that your rules are dead weight. Roasts instruction files for bloat, slop, and redundancy, then proves it by running evals. Use when user says "roast my agents.md", "roast my CLAUDE.md", "prove my rules are useless", "eval roast", or wants entertaining evidence-based feedback on their AI config files. Also triggers on "audit my instructions" or "are my rules helping".

vltansky·roast·my·agents·md
7설치·0트렌드·@vltansky

설치

GitHub: vltansky/roast-my-agents-md
$npx skills add https://github.com/vltansky/roast-my-agents-md --skill roast-my-agents-md

roast-my-agents-md 설치 방법

명령줄에서 roast-my-agents-md AI 스킬을 개발 환경에 빠르게 설치

  1. 터미널 열기: 터미널 또는 명령줄 도구(Terminal, iTerm, Windows Terminal 등)를 엽니다
  2. 설치 명령어 실행: 이 명령어를 복사하여 실행합니다: npx skills add https://github.com/vltansky/roast-my-agents-md --skill roast-my-agents-md
  3. 설치 확인: 설치 후 스킬은 자동으로 AI 코딩 환경에 설정되어 Claude Code, Cursor, OpenClaw에서 사용할 수 있습니다

출처: vltansky/roast-my-agents-md.

SKILL.md

원본 보기

Phase 1 does a quick static roast — the jokes, the sins, the token tax. Phase 2 is where it gets real: we actually run your rules through A/B tests and prove which ones the model already knows without being told. Phase 3 delivers the verdict with hard numbers.

Tone: Senior dev advocate + tech Twitter snark + Gordon Ramsay energy. Not mean-spirited, not discouraging. Punch up at patterns, not people.

Scan all instruction files in the project — root and nested. Run the audit script for data-backed roasts:

Brutally honest AGENTS.md/CLAUDE.md review backed by real A/B test evidence. Not just opinions — actual proof that your rules are dead weight. Roasts instruction files for bloat, slop, and redundancy, then proves it by running evals. Use when user says "roast my agents.md", "roast my CLAUDE.md", "prove my rules are useless", "eval roast", or wants entertaining evidence-based feedback on their AI config files. Also triggers on "audit my instructions" or "are my rules helping". 출처: vltansky/roast-my-agents-md.

인용 가능한 정보

AI/검색 인용용 안정적인 필드와 명령어.

설치 명령어
npx skills add https://github.com/vltansky/roast-my-agents-md --skill roast-my-agents-md
출처
vltansky/roast-my-agents-md
카테고리
</>개발 도구
인증됨
✓
최초 등록
2026-03-13
업데이트
2026-03-13
URL
https://www.learn-skills.dev/ko/skills/vltansky/roast-my-agents-md/roast-my-agents-md

Browse more skills from vltansky/roast-my-agents-md

빠른 답변

roast-my-agents-md이란?

Brutally honest AGENTS.md/CLAUDE.md review backed by real A/B test evidence. Not just opinions — actual proof that your rules are dead weight. Roasts instruction files for bloat, slop, and redundancy, then proves it by running evals. Use when user says "roast my agents.md", "roast my CLAUDE.md", "prove my rules are useless", "eval roast", or wants entertaining evidence-based feedback on their AI config files. Also triggers on "audit my instructions" or "are my rules helping". 출처: vltansky/roast-my-agents-md.

roast-my-agents-md 설치 방법은?

터미널 또는 명령줄 도구(Terminal, iTerm, Windows Terminal 등)를 엽니다 이 명령어를 복사하여 실행합니다: npx skills add https://github.com/vltansky/roast-my-agents-md --skill roast-my-agents-md 설치 후 스킬은 자동으로 AI 코딩 환경에 설정되어 Claude Code, Cursor, OpenClaw에서 사용할 수 있습니다

소스 저장소는 어디인가요?

https://github.com/vltansky/roast-my-agents-md

상세

카테고리
</>개발 도구
출처
skills.sh
최초 등록
2026-03-13

관련 Skills

없음