- 📁 captured/
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
This skill should be used when the user asks to "check CLI schema", "sync CLI version", "check for new CLI options", "update bundled CLI", "compare SDK structs", "check schema drift", "align message structs", "verify CLI compatibility", "check control protocol", or mentions CLI compatibility, schema alignment, or wants to ensure the SDK matches the current Claude CLI. Consolidates schema checking, options validation, control protocol coverage, and version management into a single workflow.
Build and check Lean 4 proofs. Triggers: "lean build", "check proofs", "run lean", "verify proofs", "lean".
- 📁 examples/
- 📁 references/
- 📁 scripts/
- 📄 README.md
- 📄 setup.sh
- 📄 SKILL.md
This skill should be used when the user mentions Unraid, asks to check server health, monitor array or disk status, list or restart Docker containers, start or stop VMs, read system logs, check parity status, view notifications, manage API keys, configure rclone remotes, check UPS or power status, get live CPU or memory data, force stop a VM, check disk temperatures, or perform any operation on an Unraid NAS server. Also use when the user needs to set up or configure Unraid MCP credentials.
Run comprehensive pre-press preflight checks on Adobe Illustrator documents using illustrator-mcp tools. Detects print-critical issues (RGB in CMYK, broken links, low-res images, white overprint, text not outlined), text consistency problems (dummy text, notation variations), and PDF/X compliance. Use when user asks to check a document before printing, submission, or handoff — or mentions "preflight", "pre-press check", "print check", "submission check".
- 📄 checklist.md
- 📄 common-issues.md
- 📄 quick-review.sh
Use when the user asks to review code, check for issues, or says "review", "审查", "检查代码
- 📁 references/
- 📄 README.md
- 📄 SKILL.md
Audit designs against 18 professional rules across Figma files and code (HTML/CSS/React/Vue/Tailwind). Detects framework automatically, runs category-specific code superpowers (aria, focus, contrast, tokens, responsive, motion, forms, navigation, spacing), audits for dark patterns and ethical design issues, outputs before/after code diffs, and generates a structured developer handoff report. Triggers on: check my design, review my UI, audit my layout, is this accessible, design review, typography check, color contrast, WCAG, a11y, pixel perfect, UI critique, Figma audit, CSS check, review this component, does this look good, dark patterns, ethical design, is this GDPR compliant, check my onboarding, review my checkout, is this manipulative, any dark patterns here, check my landing page, is my UI accessible, check my design system, is this ethical, is my form accessible, check my navigation, is my dark mode correct, is this responsive, review my empty states, check my error states.
Check for accessibility compliance (WCAG).
Check your InboxAPI email inbox and display a summary of recent messages. Use when the user wants to see their emails, check mail, or view their inbox.
Proactively reminds Claude Code users about relevant available tools whenever a task could benefit from them. ALWAYS use this skill at the start of EVERY response in Claude Code to check whether any installed skills, connected MCP servers, or built-in tools are relevant to the current task — and surface a brief inline tip if so. Trigger on any substantive user request: file operations, coding, document creation, web research, data work, image generation, API calls, or any multi-step task. Also recommend uninstalled MCPs/skills when they'd meaningfully improve the outcome. Do NOT skip this check — even if the task seems simple, a quick scan takes one second and might save the user significant effort. --- # Tool Advisor Skill Helps users get the most out of their Claude Code environment by surfacing relevant tools at the right moment — briefly and without interrupting flow. ## Your Job At the start of handling any substantive task, do a quick mental scan: 1. **Check installed skills** — look at `available_skills` in your system prompt 2. **Check connected MCPs** — look at MCP server list in your context 3. **Check built-in tools** — bash, file read/write, web search, image gen, etc. 4. **Consider uninstalled tools** — if a well-known MCP or skill would meaningfully help, mention it If anything relevant is found that **isn't already being used**, prepend a 💡 tip to your response. --- ## When to Tip Tip when there's a **specific, actionable match** between the task and a tool the user may not be thinking of. Do NOT tip for every response — only when it adds value. | Task type | Potentially relevant tools to check | |---|---| | Creating/editing Word docs | \`docx\` skill | | Working with PDFs | \`pdf\` skill, \`pdf-reading\` skill | | Building presentations | \`pptx\` skill | | Spreadsheet / data work | \`xlsx\` skill | | Reading uploaded files | \`file-reading\` skill | | Web research / current events | \`web_search\` tool, browser MCP | | Code execution / scripting | \
Git worktree manager for AI agent workflows. Use this skill whenever the user mentions worktrees, wants to work on a branch in isolation, check out a PR, run parallel tasks, manage stacked PRs, or sync branches. Also trigger when the project uses willow (look for ~/.willow directory, ww commands in shell history, or willow.json config). This skill is essential for any branch-switching, PR checkout, or parallel development workflow — use it instead of raw git checkout/branch commands.
Run skill design compliance validation for agentic collections. Use when the user asks to: - "Check skill compliance" / "Validate skill design" / "Run compliance check" - "Verify my skills follow design principles" - Before committing skill changes Runs the validate_skill_design.py script against SKILL_DESIGN_PRINCIPLES.md. --- # Skill Design Compliance Checker Run the programmatic compliance check for skills in this agentic-collections repository. ## When to Use This Skill
