config-doctor
Skill14 starsChanged 38 days agoMITView on GitHub
SuperClaude++ 설정 정합성 진단. scripts/config-doctor.sh를 실행해 에이전트/스킬 frontmatter, skill-rules 참조, 훅 스크립트 존재·계약, 버전·개수 정합, 문서 참조를 검사합니다.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- neeraj181-dot/ClaudeSkillstheir own version, first seen Aug 25, 2026
- liuxiao20051106-prog/claude-skillstheir own version, first seen Aug 10, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- liuxiao20051106-prog/claude-skills★ 1same name
- neeraj181-dot/ClaudeSkills★ 0same name
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 repository44 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adaptSkill
- animateSkill
- auditSkill
- bolderSkill
- brainstormSkill
- build-fixSkill
- business-panelSkill
- checkpointSkill
- clarifySkill
- colorizeSkill
- composition-patternsSkill
- confidence-checkSkill
- critiqueSkill
- delightSkill
- design-auditSkill
- devils-advocateSkill
- distillSkill
- eval-harnessSkill
- feature-plannerSkill
- fix-prSkill
- frontend-designSkill
- gap-analysisSkill
- grill-with-docsSkill
- hardenSkill
- impeccableSkill
- layoutSkill
- learnSkill
- optimizeSkill
- overdriveSkill
- polishSkill
- pytest-runnerSkill
- python-best-practicesSkill
- quieterSkill
- react-best-practicesSkill
- sc-helpSkill
- security-auditSkill
- shapeSkill
- tddSkill
- typesetSkill
- ui-ux-pro-maxSkill
- uv-packageSkill
- verifySkill
- web-design-guidelinesSkill
The file
Files
Config Doctor
Purpose
SuperClaude++ 설정의 무결성을 기계적으로 검증합니다. 모든 검사는
scripts/config-doctor.sh 한 스크립트에 있고, 같은 스크립트가 CI에서도 돕니다.
문서와 코드가 어긋나면(개수, 버전, 존재하지 않는 스크립트 경로) 여기서 잡힙니다.
Dynamic Context
Current framework version:
!python3 -c "import json; print(json.load(open('plugin.json'))['version'])" 2>/dev/null || echo "plugin.json not found (run from repo root)"
Run
bash scripts/config-doctor.sh # 전체 진단 (❌ 있으면 exit 1)
bash scripts/config-doctor.sh --quiet # ❌/⚠️ 만 출력
bash tests/hooks/run.sh # 훅 계약 픽스처 테스트 (27 cases)Checks (config-doctor.sh)
| # | 검사 | 실패 시 | |
| 1 | agents/*.md frontmatter — name description model tools maxTurns effort, name == 파일명 | ❌ | |
| 2 | skills/*/SKILL.md 존재 + frontmatter(description 필수), name == 디렉터리 | ❌ / ⚠️ | |
| 3 | .claude/skill-rules.json — 파싱, 중복 rule, 대상 스킬 존재, regex 컴파일 | ❌ | |
| 4 | config/settings.json hooks — ~/.claude/scripts/* 명령이 저장소에 존재(❌)·설치됨(⚠️), timeout > 600이면 ms 오기(❌), CLAUDE_* 환경변수 의존(❌), statusLine 경로 | ❌ / ⚠️ | |
| 5 | 버전·개수 — plugin.json == CHANGELOG 최상단 == CHANGELOG 표 행, README/CLAUDE.md 제목 major.minor, README 헤드라인·### Skills (N개 == 실제 스킬/에이전트 수, InstructionsLoaded 배너 | ❌ / ⚠️ | |
| 6 | 참조 파일 — CLAUDE.md On-Demand 목록의 optional/*.md, MODES/RULES가 가리키는 optional/, 문서가 언급하는 `scripts/*.sh | py`, 스킬 심볼릭 링크 | ❌ |
| 7 | 문법 — bash -n, py_compile, JSON 파싱, shellcheck(설치 시) | ❌ / ⚠️ |
Output
▶ 1. Agent frontmatter (agents/*.md)
· 9 agents checked
...
════════════════════════════════════════
Config Doctor: 0 error(s), 1 warning(s)
Framework Health: HEALTHY
════════════════════════════════════════HEALTHY가 아니면 ❌ 항목을 먼저 고치세요. ⚠️는 CI를 막지 않습니다.
Adding a check
새 드리프트 유형을 발견하면 scripts/config-doctor.sh의 해당 섹션에 err/warn 한 줄을
추가합니다. 문서에 규칙을 적는 것보다 스크립트가 잡는 쪽이 유지됩니다(PRINCIPLES.md
"Machine-readable Constraints").
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
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.