菜单
Use when you need to analyze changes and ensure verify-* skill coverage.
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
| name | team-shinchan:manage-skills |
| description | Use when you need to analyze changes and ensure verify-* skill coverage. |
| user-invocable | false |
When this skill is invoked, execute immediately. Do not explain.
git status --porcelain && git diff --name-only HEAD~1
Exempt paths (not verification targets): .shinchan-docs/**, docs/**, WORKFLOW_STATE.yaml, tests/validate/**, node_modules/**, .git/**
Verification targets: agents/.md, skills//SKILL.md, hooks/*.md, CLAUDE.md, tests/** (except validators)
| Changed Path | Verify Skill | Validators |
|---|---|---|
agents/*.md, agents/_shared/*.md | verify-agents | agent-schema, shared-refs |
skills/*/SKILL.md | verify-skills | skill-schema, skill-format, input-validation |
CLAUDE.md | verify-consistency | cross-refs, stage-matrix, debate-consistency |
docs/workflow-guide.md, hooks/*.md | verify-workflow | workflow-state-schema, error-handling, quick-fix-path |
agents/*-part-*.md | verify-workflow | part-numbering |
| Memory-related sections | verify-memory | memory-system |
| Any file creation/expansion | verify-budget | token-budget |
hooks/hooks.json, plugin.json | verify-workflow | hook-registration |
skills/*/SKILL.md, commands/*.md | verify-skills | skill-command-parity |
plugin.json, marketplace.json, README.md, CHANGELOG.md | verify-consistency | version-consistency |
Total: 17 validators across 7 verify-* skills.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔧 [Skill Manager] Coverage Analysis
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 Changed files: {count}
✅ Covered: {file → verify-skill (validators)}
⚠️ Uncovered: {file → No matching skill}
📋 Run: cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/index.js
*.md from analysis (they ARE the codebase)src/ directories — out of scope for THIS skill (manage-skills maps only the markdown harness surface; the src/ JS engine layer is documented in CLAUDE.md § "Source Layer (src/)")tests/validate/All changed files analyzed, each mapped to verify-* skill, gaps identified, validator commands listed.
Use when you have a large-scale, multi-phase project requiring orchestrated execution.
Use when you need persistent looping until a task is fully complete.
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.
Use when the user wants to review accumulated skill feedback, verdict trends, or improvement candidates collected during Stage 4 retrospectives. Trigger on "show skill feedback", "스킬 피드백 보여줘", or finding which skills need /writing-skills work.
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.