Engineering agent skills
Curated engineering SKILL.md files for Cursor, Claude Code, VS Code, and Codex. Copy, download, and install in your agent.
22 skills
Agent Browser
Browser automation for AI agents: open URLs, snapshot elements, click, fill, screenshot, and run real user-flow QA sessions from the CLI.
Vercel React Best Practices
Dense React and Next.js best practices: performance, data fetching, server components, patterns, and opinionated reviews with good/bad examples.
Vercel Composition Patterns
React composition patterns for scalable UI: compound components, slot APIs, state lifting, and architecture that keeps design systems maintainable.
Deploy to Vercel
Deploy projects to Vercel from the agent: environment setup, build configuration, preview URLs, and production deployment workflows.
Remotion Render
Render MP4 videos from React/Remotion TSX via the inference.sh belt CLI. Pass component code with useCurrentFrame, spring, and Sequence — get programmatic motion graphics without a local Remotion studio.
Find Skills
Discover and install agent skills from the open ecosystem. Search skills.sh, verify quality, and install with npx skills when users need capabilities beyond your current setup.
Vibe Coding
Build software with AI coding tools as a non-traditional developer: prompting patterns, iteration loops, and shipping working prototypes in Cursor or Claude Code.
Web Artifacts Builder
Build elaborate, multi-component React artifacts with Tailwind CSS and shadcn/ui. Full stack for creating production-ready web components and applications.
Remotion Best Practices
Domain-specific knowledge for Remotion: compositions, animations, sequencing, transitions, video/audio/assets, Lottie, charts, captions, and more.
gstack
Fast headless browser for QA testing, deployment verification, and user-flow dogfooding. Navigate pages, interact with elements, diff snapshots, take annotated screenshots, and test responsive layouts, forms, and dialogs.
Using Superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Systematic Debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Requesting Code Review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Test-Driven Development
Use when implementing any feature or bugfix, before writing implementation code
Executing Plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Subagent-Driven Development
Use when executing implementation plans with independent tasks in the current session
Verification Before Completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertion...
Receiving Code Review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or bli...
Writing Skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Dispatching Parallel Agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Using Git Worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
Finishing a Development Branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup