Relentlessly interviews you about your plan, feature, or design until every edge case, failure mode, and assumption is resolved. Does NOT implement anything — only asks probing questions. Use before starting implementation to bulletproof your thinking.
End-of-session summary written to .claude/memory/handoffs/ .md so the next session can pick up cleanly. Captures what was done, what's pending, what's blocked, what to verify, and any decisions awaiting the user.
Scaffolds production-ready legal page templates for a website: Privacy Policy, Terms of Service, Cookie Policy, Cookie Consent banner, Refund Policy, Contact / Imprint. Templates are clearly marked as a starting point — the user must customize and have a lawyer review before going live.
Inherit memories from another workspace. Reads .claude/memory/ from a source path and imports its memories into the current workspace under .claude/memory/inherited/ /. Tagged with provenance so the user can tell where each came from.
Manage the persistent memory layer in .claude/memory/ — list, search, save, update, delete, dedupe. Use to inspect what memories exist, write a new one, or clean up stale entries.
Assists with migrating between frameworks or major versions — Express to Fastify, CRA to Vite, Vue 2 to Vue 3, class components to hooks, etc. Creates a migration plan, identifies breaking changes, and provides file-by-file migration order.
Generates a comprehensive codebase onboarding guide by scanning the project structure, detecting the stack, mapping architecture, and identifying key entry points. Use when joining a new project or onboarding teammates.
Analyzes code for performance bottlenecks and produces prioritized, actionable optimization recommendations with before/after code. Use before shipping performance-critical features or when code feels slow.
Generates a well-structured pull request description from the current branch diff. Includes summary, changes list, test plan, and breaking changes. Use before opening a PR.
Analyzes code for smells and structural issues, proposes a safe refactoring plan, and executes it with test verification. Use when code is hard to read, maintain, or extend.
Analyze a fully-built reference application that the user wants to use as a model. Reads its architecture, conventions, tech stack, and patterns; stores a structured summary in .claude/memory/reference/ so subsequent sessions can compare the current project against it.
Performs a comprehensive pull request code review covering correctness, security, performance, test coverage, and coding standards. Use when reviewing any code changes before merge.
Scans the codebase for security vulnerabilities including injection flaws, authentication issues, hardcoded secrets, and insecure configurations. Run before any PR touching auth, user input, or external APIs.
Scaffolds production-grade SEO for any website: per-page meta tags, Open Graph, Twitter Cards, canonical URLs, JSON-LD structured data, sitemap.xml, robots.txt, and security.txt. Auto-detects the framework and uses its idiomatic approach (Next.js metadata API, Astro layouts, etc.).
Implements features using strict test-driven development — red-green-refactor cycle. Writes a failing test first, then minimal code to pass, then refactors. Use when building features that need high reliability.
Pre-launch audit for any website. Verifies privacy policy, ToS, cookie consent, sessions, sitemap, robots.txt, SEO meta tags, structured data, accessibility (WCAG AA), Core Web Vitals, and compliance frameworks (GDPR/CCPA). Returns severity-graded findings with a GO / NO-GO verdict.
Generates textual or ASCII wireframes for screens, layouts, and information architecture. Pixel-free; focused on structure, hierarchy, and component placement. Output is reviewable in a PR diff and translates directly to component code.
Meta-skill that creates new Claude Code skills. Describe what you want the skill to do and this generates a complete SKILL.md with proper frontmatter, shell injection, structured instructions, and output format.
Generates comprehensive unit and integration tests for a specified file or function. Auto-detects the test framework, follows existing patterns, and covers happy path, edge cases, error conditions, and async behavior. Use when adding tests to untested code or TDD-ing a new module.
★not rated 7 4mo agoA60 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: