メニュー
Audit and optimize skills for token efficiency and progressive disclosure compliance. Use when user wants to "analyze skill tokens", "audit skills", "optimize skill size", "check token efficiency", or "validate progressive disclosure".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
This skill should be used when the user wants to run Claude with risk-based permission enforcement, configure safe mode settings, create permission blocks for SAFEGUARDS.md files, or understand how to restrict CLI operations based on risk levels. Use when asked about "safe mode", "permission enforcement", "risk levels", "claude-safe", or "restricting dangerous commands".
Build and scaffold Assistant Skills plugin projects. This skill should be used when: (1) create new Claude Code plugin project, (2) add skill to existing project, (3) scaffold CLI library for API, (4) wrap existing CLI tool, (5) validate project structure, (6) migrate existing project to new structure, (7) show reference patterns from production implementations (Jira, Confluence, Splunk).
Create production-ready demo platforms for Assistant Skills plugins. Use when you want to "create a demo", "scaffold demo infrastructure", "set up demo for plugin", "generate demo project", or need to create queue-managed demo environments like jira-demo, confluence-demo, or splunk-demo.
Set up end-to-end testing infrastructure for Assistant Skills plugins. Use when user wants to "add E2E tests", "test my plugin", "set up integration testing", "create plugin tests", or needs to validate their Claude Code plugin works correctly with real API calls.
Extract shared libraries from Assistant Skills projects and publish them as PyPI packages. Use when user wants to "publish shared library", "create PyPI package", "extract library to package", "migrate to pip install", or needs to convert vendored code into an installable package with CI/CD.
Create professional README landing pages for Assistant Skills projects with consistent branding. Use when creating or upgrading project READMEs, generating logos, or ensuring visual consistency across repositories.
| name | skills-optimizer |
| description | Audit and optimize skills for token efficiency and progressive disclosure compliance. Use when user wants to "analyze skill tokens", "audit skills", "optimize skill size", "check token efficiency", or "validate progressive disclosure". |
Audit skills for token efficiency and progressive disclosure compliance.
| Operation | Script | Description |
|---|---|---|
| Analyze Skill | analyze-skill.sh | Audit single skill's token footprint |
| Audit All | audit-all-skills.sh | Batch audit entire skills directory |
| Validate | validate-skill.sh | Check structure and compliance |
./scripts/analyze-skill.sh ~/.claude/skills/my-skill
# Output: Token count, violations, recommendations
./scripts/audit-all-skills.sh ~/.claude/skills
# Generates: audit-report.json with per-skill scores
| Level | Target | Loaded When | Contains |
|---|---|---|---|
| L1: Metadata | ~200 chars | Startup (all skills) | name, description, triggers |
| L2: SKILL.md | <500 lines | Skill triggered | Quick start, workflow overview |
| L3: Nested docs | Variable | Explicitly accessed | API refs, examples, guides |
wc -w SKILL.md (target: <2000 words)./scripts/validate-skill.sh| Violation | Detection | Fix |
|---|---|---|
| Bloated description | >1024 chars | Trim, front-load keywords |
| Voodoo constants | Explains PDF/JSON/API | Delete (Claude knows) |
| Inline code dumps | >50 line blocks | Move to scripts/ |
| Deep nesting | A→B→C chains | Flatten to one level |
Automatically detected for skills mentioning "hub", "router", or "routes to...skills":
| Check | Description | Severity |
|---|---|---|
| R001 | Quick Reference table with Risk column | Warning |
| R002 | Risk Legend present | Warning |
| R003 | Negative Triggers documented | Warning |
| R004 | Disambiguation examples | Warning |
| R005 | Context awareness (pronoun resolution) | Info |
Applied to skills with scripts/ directory:
| Check | Description | Severity |
|---|---|---|
| K001 | Destructive scripts have ⚠️ indicators | Warning |
| K002 | Bulk operations marked as ⚠️⚠️ | Warning |
| K003 | High-risk ops document --dry-run | Warning |
| Risk | Symbol | Operations | Required Safeguards |
|---|---|---|---|
| Safe | - | search, list, get, export | None |
| Destructive | ⚠️ | create, update, delete | Confirm |
| High-risk | ⚠️⚠️ | bulk ops, admin changes | Confirm + dry-run |
{
"skill": "my-skill",
"tokenFootprint": { "level1": 180, "level2": 3200, "level3": 15000 },
"violations": [...],
"score": 72,
"grade": "C"
}