一键导入
config-doctor
SuperClaude++ 설정 유효성 검증. AGENT.md frontmatter, skill-rules.json, hook 스크립트 경로 등 전체 설정을 진단합니다.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
SuperClaude++ 설정 유효성 검증. AGENT.md frontmatter, skill-rules.json, hook 스크립트 경로 등 전체 설정을 진단합니다.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Interactive requirements discovery through Socratic dialogue and systematic exploration
사용자 계획을 기존 도메인 모델에 대해 stress-test하는 인터뷰 세션. 용어를 날카롭게 다듬고, 결정이 굳어질 때마다 CONTEXT.md(도메인 어휘 사전)와 ADR을 인라인으로 갱신한다. 새 기능 요구사항 탐색은 `/brainstorm`을, 기존 도메인 모델·용어와의 정합성 점검은 이 스킬을 사용한다.
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review. (Impeccable design audit — distinct from /audit which validates project rules.)
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for shape-then-build, 'teach' for design context setup, or 'extract' to pull reusable components and tokens into the design system.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
| name | config-doctor |
| description | SuperClaude++ 설정 유효성 검증. AGENT.md frontmatter, skill-rules.json, hook 스크립트 경로 등 전체 설정을 진단합니다. |
| user-invocable | true |
SuperClaude++ v2.0 프레임워크의 설정 무결성을 검증합니다.
Current framework version:
!cat .superclaude-metadata.json 2>/dev/null | python3 -c "import sys,json; print(json.load(sys.stdin).get('framework',{}).get('version','unknown'))" 2>/dev/null || echo "metadata not found"
모든 agents/*.md 파일에 필수 frontmatter 필드 존재 확인:
name (필수)description (필수)model (필수: haiku | sonnet | opus)tools (필수)maxTurns (필수)effort (필수: low | medium | high | max)for f in agents/*.md; do
echo "Checking $f..."
head -20 "$f" | grep -q "^model:" || echo " ❌ Missing: model"
head -20 "$f" | grep -q "^tools:" || echo " ❌ Missing: tools"
head -20 "$f" | grep -q "^maxTurns:" || echo " ❌ Missing: maxTurns"
head -20 "$f" | grep -q "^effort:" || echo " ❌ Missing: effort"
done
.claude/skill-rules.json 문법 및 참조 검증:
skill 이 skills/ 에 실제 존재하는지python3 -c "
import json, os, re
rules = json.load(open('.claude/skill-rules.json'))
for rule in rules.get('rules', []):
skill = rule['skill']
if not os.path.isdir(f'skills/{skill}'):
print(f' ❌ Skill not found: {skill}')
for pat in rule.get('triggers', {}).get('prompt_patterns', []):
try:
re.compile(pat)
except re.error as e:
print(f' ❌ Invalid regex in {skill}: {pat} ({e})')
print('Skill rules validation complete.')
"
config/settings.json의 모든 hook command 경로가 유효한지 확인:
python3 -c "
import json, os
settings = json.load(open('config/settings.json'))
for hook_type, entries in settings.get('hooks', {}).items():
for entry in entries:
for hook in entry.get('hooks', []):
cmd = hook.get('command', '')
if cmd and not cmd.startswith('echo') and not cmd.startswith('python3'):
script = cmd.split()[0].replace('~', os.path.expanduser('~'))
if not os.path.exists(script):
print(f' ⚠️ {hook_type}: Script not found: {script}')
print('Hook path validation complete.')
"
모든 skills/*/ 디렉토리에 SKILL.md가 존재하는지:
for d in skills/*/; do
[ ! -f "$d/SKILL.md" ] && echo " ⚠️ Missing SKILL.md: $d"
done
설정된 MCP 서버의 실행 가능 여부:
python3 -c "
import json, os
settings = json.load(open('config/settings.json'))
for name, config in settings.get('mcpServers', {}).items():
cmd = config.get('command', '')
print(f' MCP {name}: command={cmd}')
"
╔══════════════════════════════════════════════╗
║ 🏥 CONFIG DOCTOR REPORT ║
╠══════════════════════════════════════════════╣
║ 1. Agent Frontmatter ✅/❌ (N issues) ║
║ 2. Skill Rules ✅/❌ (N issues) ║
║ 3. Hook Scripts ✅/❌ (N issues) ║
║ 4. Skills Integrity ✅/❌ (N issues) ║
║ 5. MCP Servers ✅/❌ (N issues) ║
╠══════════════════════════════════════════════╣
║ Total Issues: N ║
║ Framework Health: HEALTHY / DEGRADED / BROKEN║
╚══════════════════════════════════════════════╝
/config-doctor # Full diagnostic
/config-doctor --quick # Checks 1-4 only (skip MCP)