codex
OpenAI Codex second opinion via the codex CLI — three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial pass that tries to break the code. Consult: ask Codex anything, with session continuity for follow-ups. Use when the user says \"codex review\", \"codex challenge\", \"ask codex\", or wants a second opinion from Codex.
dependency-safety-check
Screens third-party project dependencies for known vulnerabilities and supply-chain risk before installation using a bundled check-deps.py script. Use when user asks to install, add, update, upgrade, or pin packages with npm, pnpm, yarn, bun, pip, uv, poetry, or cargo, or when deciding whether a package version is safe to install. Do NOT use for OS package managers such as apt, brew, yum, apk, or pacman.
design-md
Create, update, validate, diff, or export DESIGN.md files following the Google Stitch DESIGN.md spec and @google/design.md tooling. Use when the user asks to write/update DESIGN.md, create a design system document, generate design tokens, encode brand/UI guidelines, export a design system, or document UI consistency rules for AI agents. Do NOT use for ordinary UI implementation unless the user asks for DESIGN.md or design-system documentation.
git-hook
Assess, adopt, or harden repository-local Git-hook automation. Use when setting up or standardizing project hooks, choosing between Lefthook and git-hook-pure, migrating an existing hook manager, reusing hook configuration or scripts, or bootstrapping hooks for fresh clones.
agent-centric
Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.
command-creator
Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, custom prompt shortcut, or workflow automation command for Claude Code. Helps define command structure, frontmatter, arguments, and best practices.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
mcp-context7
Query up-to-date library documentation and code examples using Context7. Provides 2 tools for resolving library IDs and querying documentation.
grill-me
Stress-test a plan, design, decision, or idea through a focused interview. Use when the user asks to be grilled, challenge their thinking, or resolve design choices before proceeding.
grok
xAI Grok second opinion via the grok CLI — three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial pass that tries to break the code. Consult: ask Grok anything, with session continuity for follow-ups. Use when the user says \"grok review\", \"grok challenge\", \"ask grok\", or wants a second opinion from Grok.
guardrails
Rendered guardrail framework: keep a repo's hard rules in one-rule-per-file GRL sources behind a compact router, and render only the rules a task needs. Use when gathering guardrail context before implementing or reviewing code, when creating, editing, retiring, or reviewing GRL rule files or .agents/guardrails/index.md, when running the guardrails CLI (validate, render, review-metadata, next-id), or when setting up, adopting, or bootstrapping a guardrail framework in a repo that does not have one yet. Do NOT use for ordinary lint rule authoring unless the lint rule backs a guardrail, for runtime safety guardrails such as rate limiting, destructive-command protection, or input validation, for LLM or AI output guardrails, or for soft conventions and style preferences that are not hard rules.
mcp-deepwiki
Access and query GitHub repository documentation using DeepWiki's AI-powered knowledge base. Provides 3 tools for browsing documentation structure, viewing content, and asking questions.
mcp-fetch
Web content fetching and conversion to markdown for efficient LLM consumption. Provides 1 tool for fetching URLs and extracting content.
mcp-grep
Search over a million GitHub repositories for real-world code examples using grep.app. Find literal code patterns, usage examples, and implementation patterns across popular open-source projects. Perfect for discovering how developers use specific APIs, libraries, or coding patterns.
mcp-skill-generator
Convert MCP servers to Claude Code skills with progressive disclosure. Use when creating a skill from an MCP server, updating an existing MCP skill, or converting MCP documentation to skill format. Accepts MCP documentation URLs, npm package names, or direct connection info.
parallel-agent-workflow
Coordinate multiple agents working in parallel using git worktrees to avoid file conflicts. Use when needing concurrent agents to modify different files/components with worktree isolation, or when asked to use worktrees for parallel agent work.
pi-extension-dev
End-to-end workflow for developing, debugging, configuring, and shipping pi-coding-agent extensions and pi packages. Use when building or maintaining extensions, skills, prompt templates, themes, settings.json setups, provider integrations, or when updating this skill after pi releases. Do NOT use for general coding questions unrelated to pi extension development.
playwright
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
seo-article-optimizer
Optimize single articles or landing pages for SEO. Analyzes keywords, readability, headings, meta tags, internal links, E-E-A-T signals, featured snippets. Outputs scores, optimized draft, and publish assets. Use for blog posts, landing pages, or single URL optimization.
seo-site-audit
Website-level technical SEO audit with engineering backlog. Covers robots.txt, sitemap, canonical, redirects, meta/OG/Twitter, JSON-LD, internal linking, Core Web Vitals, mobile. Use for site-wide SEO improvements or technical SEO implementation.
show-me
Make the current discussion concrete with diagrams, code-shape sketches, and focused HTML artifacts. Use when the user asks to see a structure, flow, relationship, layout, or before-and-after change.
skill-composer
Use when the user asks to create a new Agent Skill, revise an existing skill's authored behavior or activation, audit a complete skill package, design its eval suite, port it across agent harnesses, or prepare and validate its release. When a generic skill-authoring helper overlaps, this skill owns scope, structure, portability, validation, and release history. If the work neither changes nor audits an Agent Skill package, do not load this skill.
teach-me
Explain an unfamiliar topic to a beginner with a visual HTML explainer. Use when the user asks to learn a concept from scratch, requests ELI5, or wants a simple picture-led explanation.