Use Cursor's browser aria snapshots to audit a page for accessibility issues — missing labels, broken tab order, contrast, and ARIA misuse. Use when the user says "/accessibility-auditing", "accessibility auditing", or asks about accessibility auditing.
Generate OpenAPI/Swagger documentation for an API, including endpoint schemas, request/response types, and interactive docs UI. Use when the user says "/adding-api-docs", "adding api docs", or asks about adding api docs.
Start the dev server, discover API routes from the codebase, hit every endpoint, and report which ones return errors. Use when the user says "/api-smoke-testing", "api smoke testing", or asks about api smoke testing.
Document technical decisions as Architecture Decision Records (ADRs) with context, options considered, and rationale. Use when the user says "/architecture-decision-records", "architecture decision records", or asks about architecture decision records.
Audit and optimize application performance, including bundle size, rendering, database queries, and Core Web Vitals. Use when the user says "/auditing-performance", "auditing performance", or asks about auditing performance.
Run TypeScript type checking after file edits and immediately flag type errors before moving on. Uses Cursor hooks for automatic enforcement. Use when the user says "/auto-type-checking", "auto type checking", or asks about auto type checking.
Monitor a pull request for CI failures, review comments, and merge conflicts — then fix them automatically. Use when a PR is open and you want the agent to keep it merge-ready. Use when the user says "/babysitting-pr", "babysitting pr", or asks about babysitting pr.
Solve a hard problem by trying multiple approaches in parallel using isolated git worktrees. Each attempt runs in its own branch, and the best solution is selected. Use for complex refactors, tricky bugs, or architectural decisions where multiple strategies could work. Use when the user says "/best-of-n-solving", "best of n solving", or asks about best of n solving.
When the same multi-step workflow repeats in Cursor (user corrections or agent redos), capture it as a new SKILL.md under .cursor/skills/ so future sessions load it automatically. Use when the user says "/building-skills-from-patterns", "building skills from patterns", or asks about building skills from patterns.
Check out two branches in separate worktrees, start both dev servers on different ports, screenshot the same pages, and produce a visual diff. Use when the user says "/comparing-branches-visually", "comparing branches visually", or asks about comparing branches visually.
Migrate CSS Modules (.module.css/.module.scss) to Tailwind utility classes. Handles styles object removal, className interpolation, composition, and global overrides. Use when the user says "/converting-css-modules-to-tailwind", "converting css modules to tailwind", or asks about converting css modules to tailwind.
Convert plain CSS stylesheets to Tailwind CSS utility classes. Handles selectors, media queries, pseudo-classes, custom properties, and animations. Use when the user says "/converting-css-to-tailwind", "converting css to tailwind", or asks about converting css to tailwind.
Toggle between light and dark mode in Cursor's browser, screenshot both states, and flag missing token mappings or contrast issues. Use when the user says "/dark-mode-testing", "dark mode testing", or asks about dark mode testing.
Design database schemas — tables, relationships, indexes, constraints, and ORM setup. Covers relational design, normalization, and common patterns. Use when the user says "/database-design", "database design", or asks about database design.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice". Use when the user says "/design-an-interface", "design an interface", or asks about design an interface.
Detect EADDRINUSE and port conflicts, find what's using the port, and resolve it by killing the process or suggesting an alternative port. Use when the user says "/detecting-port-conflicts", "detecting port conflicts", or asks about detecting port conflicts.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. Use when the user says "/domain-model", "domain model", or asks about domain model.
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft. Use when the user says "/edit-article", "edit article", or asks about edit article.
Export code, terminal output, diagrams, or UI components to PNG images using headless browser rendering or CLI tools. Use when the user says "/exporting-to-png", "exporting to png", or asks about exporting to png.
Scan running terminals for dev server URLs (localhost ports), report them, and optionally open the app in Cursor's built-in browser. Use when the user says "/finding-dev-server-url", "finding dev server url", or asks about finding dev server url.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.