NeVibeCode · repository · 64 items
awesome-cursor-skills: a set by spencerpauly
The spencerpauly/awesome-cursor-skills repository on GitHub: 64 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- spencerpauly/awesome-cursor-skills
- Stars
- ★ 898
- Installs across cards
- 31,145
- License
- CC0-1.0
- Source updated
- 2026-08-02
- In the catalog since
- 2026-10-26
visual-qa-testing skill visual-qa-testing is a Claude Code skill that opens the built-in browser, captures a page screenshot, and checks console errors after UI changes while the dev server is running.
CX Codex +1
714installs
auditing-security skill auditing-security audits codebases for hardcoded secrets, OWASP Top 10 flaws, and insecure settings. Helps spot security risks before shipping code.
CX Codex +1
647installs
responsive-testing skill responsive-testing — a skill that loads your app in Cursor's browser at five viewport widths, screenshots each one and flags broken layout.
CX Codex +1
632installs
suggesting-cursor-rules skill suggesting-cursor-rules watches for repeated code corrections and suggests saving them as Cursor rules. It helps lock project conventions so you do not repeat the same instructions.
CX Codex +1
607installs
grinding-until-pass skill grinding-until-pass — a skill that keeps the agent in a fix → run → check loop until tests pass, the build succeeds or linting comes back clean.
CX Codex +1
605installs
systematic-debugging skill systematic-debugging enforces a structured debugging workflow on your AI assistant instead of random edits. It helps isolate elusive bugs and verify root causes with evidence.
CX Codex +1
604installs
verifying-in-browser skill verifying-in-browser starts the dev server after code changes, opens the app in a browser and checks rendering, console errors and network health.
CX Codex +1
602installs
using-ui-stack skill using-ui-stack makes the agent build interfaces from fixed rules: an 8px grid, 60-30-10 colors, type scale, dark mode and interaction states.
CX Codex +1
586installs
parallel-code-review skill parallel-code-review runs four parallel read-only subagents to inspect a diff across security, speed, correctness, and readability. Built for vetting large or risky pull requests.
CX Codex +1
582installs
reviewing-code skill reviewing-code — a skill that walks your code through a checklist: correctness, maintainability, performance, types and tests. Useful when a change needs review before merge.
CX Codex +1
562installs
writing-tests skill writing-tests inspects existing code, detects your test runner, and drafts unit and integration tests with mocks and edge cases.
CX Codex +1
550installs
saving-workspace-context skill The saving-workspace-context skill writes research, decisions and templates into your workspace files, so the next session starts with context instead of a blank slate.
CX Codex +1
545installs
api-smoke-testing skill api-smoke-testing finds API endpoints across your codebase, spins up the local dev server, and tests every route with curl. Spots unmounted 404 routes and 500 server crashes before release.
CX Codex +1
544installs
codebase-onboarding skill codebase-onboarding — a skill for Claude Code, Cursor, Codex, GitHub Copilot, and Gemini CLI that fires five subagents in parallel and writes their findings into a single ONBOARDING.md.
CX Codex +1
527installs
auditing-performance skill auditing-performance — a skill that audits app performance: bundle size, rendering, database queries and Core Web Vitals. Useful when pages load slowly or the UI stutters.
CX Codex +1
518installs
suggesting-cursor-hooks skill suggesting-cursor-hooks watches for repetitive check requests and suggests automating them with Cursor hooks. Useful when you find yourself repeatedly asking the agent to run linters or tests.
CX Codex +1
517installs
building-skills-from-patterns skill building-skills-from-patterns turns repeated multi-step workflows into reusable SKILL.md files. It triggers when an agent re-derives the same routine or needs the same user correction three times.
CX Codex +1
514installs
parallel-exploring skill parallel-exploring launches several explore subagents at once so you can map a large codebase fast. Useful for onboarding and for tracing a feature across layers.
CX Codex +1
511installs
database-design skill database-design designs relational database schemas, foreign keys, indexes, and constraints from raw requirements, with output tailored for SQL, Prisma, or Drizzle.
CX Codex +1
505installs
creating-pr skill creating-pr — a skill that walks the agent through opening a pull request: branch prep, title, structured description, self-review and reviewer requests.
CX Codex +1
505installs
writing-commit-messages skill The writing-commit-messages skill gives the agent a fixed format for commit messages: type, scope, body, footer. Useful when the model writes the commits, not you.
CX Codex +1
499installs
seo-auditing skill seo-auditing audits technical SEO in web projects, covering meta tags, structured data, robots.txt, sitemaps, and Core Web Vitals. Useful before shipping pages to production.
CX Codex +1
498installs
form-testing skill form-testing — a skill for Claude Code, Codex, Cursor and other platforms that walks every form in the app and checks validation, error states, and success flows. Triggered on demand by the user.
CX Codex +1
493installs
monitoring-terminal-errors skill monitoring-terminal-errors — a skill that watches a running process — dev server, test runner, build — for crashes and stack traces, then opens the failing file and fixes it. Handy when the log is long and the error is buried.
CX Codex +1
493installs
architecture-decision-records skill architecture-decision-records is a Claude Code skill that records technical choices as ADRs, including context, alternatives, rationale, and consequences. It covers decisions that are hard to reverse or affect several parts of a system.
CX Codex +1
492installs
suggesting-skills skill suggesting-skills — a skill that watches what you're doing and suggests installing another skill when one already covers the task. Useful when you don't know the set yet.
CX Codex +1
486installs
adding-e2e-tests skill adding-e2e-tests — a skill that walks your agent through Playwright setup: config, a smoke test, npm scripts and a CI run.
CX Codex +1
486installs
auto-type-checking skill auto-type-checking runs tsc --noEmit after each TypeScript edit and surfaces type errors right away instead of at build time.
CX Codex +1
479installs
network-request-auditing skill network-request-auditing is a Claude Code skill that inspects browser network traffic after user actions. It flags failures, slow responses, repeated calls, and suspicious data on API-heavy pages or after networking changes.
CX Codex +1
479installs
dark-mode-testing skill dark-mode-testing toggles light and dark mode in the browser, screenshots both states, and points out hardcoded colors, invisible text and contrast failures.
CX Codex +1
478installs
writing-copy skill writing-copy — a skill that gives the agent rules for marketing copy: headlines, CTAs, emails, interface microcopy. Useful when landing pages and UI text live in the same repo.
CX Codex +1
475installs
babysitting-pr skill babysitting-pr monitors an open pull request for CI failures, review comments, and merge conflicts, then fixes issues locally and pushes updates.
CX Codex +1
467installs
finding-dev-server-url skill finding-dev-server-url scans running terminal sessions for dev server URLs and localhost ports. Useful when you need to locate active local endpoints or check port collisions.
CX Codex +1
465installs
converting-css-to-tailwind skill The converting-css-to-tailwind skill walks a plain CSS file and rewrites its rules as Tailwind utility classes in your markup. Handy when a project moves off hand-written CSS.
CX Codex +1
463installs
best-of-n-solving skill best-of-n-solving runs two or three approaches to a hard problem at once, each in its own git worktree, then helps you pick the winner.
CX Codex +1
463installs
detecting-port-conflicts skill detecting-port-conflicts detects EADDRINUSE and port conflicts in terminal output, identifies blocking processes with lsof, and kills them or picks an open port for your dev server.
CX Codex +1
459installs
setting-up-ci skill setting-up-ci — a skill that writes a GitHub Actions pipeline with linting, tests, type-checking and a deploy step. Useful when the repo has no CI yet.
CX Codex +1
458installs
prompt-engineering skill The prompt-engineering skill explains how to design prompts with examples, constraints, and fixed output formats. It fits code tasks, classification, and response parsing.
CX Codex +1
456installs
adding-api-docs skill The adding-api-docs skill writes OpenAPI/Swagger documentation for an API: endpoint schemas, request and response types, and an interactive docs page.
CX Codex +1
455installs
parallel-test-fixing skill The parallel-test-fixing skill runs your test suite and assigns each failing test file to a separate subagent for parallel fixes. It helps when multiple test files break simultaneously across a codebase.
CX Codex +1
455installs
1–40 of 64