frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build 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.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
context7
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
prd
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
ralph
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
groq-api
Groq API integration for building AI-powered applications with ultra-fast LLM inference. Use when working with Groq's Chat Completions API, Python SDK (groq), TypeScript SDK (groq-sdk), tool use/function calling, vision/image processing, audio transcription with Whisper, streaming responses, text-to-speech, content moderation with Llama Guard, batch processing, or any Groq API integration task. Triggers on mentions of Groq, GroqCloud, or fast LLM inference needs.
seo-analyzer
基于 Google 官方文档的 SEO 自动检测工具。自动分析网址的技术 SEO、内容元数据、性能体验和链接结构，输出符合 Google 最佳实践的检测报告。使用场景：(1) 分析网站 SEO 状况，(2) 诊断搜索引擎排名问题，(3) 验证页面是否符合 Google Search Essentials 标准，(4) 生成可执行的 SEO 优化建议。
tool-polymarket-book
Use the polymarket_book tool to fetch Polymarket CLOB order book depth (YES/NO) via Gamma + CLOB and expose best bid/ask/mid.
tool-coingecko-price
Use the coingecko_price tool to fetch spot crypto prices (free) for one or more symbols/ids with 24h change and last-updated timestamps.
tool-gdelt-news
Use the gdelt_news tool to fetch recent headlines via GDELT (free) with shared caching, rate limiting, and basic query normalization.
tool-grok-search
Use the grok_search tool to search X/web/news via xAI Grok Live Search (paid) and return an answer plus citations.
tool-nasdaq-candles
Use the nasdaq_candles tool to fetch OHLCV candles (free) with caching and latency metadata; good for quick charting.
tool-nasdaq-quote
Use the nasdaq_quote tool to fetch a US equity quote (free; delayed) with lightweight caching and latency metadata.
tool-polymarket-trades
Use the polymarket_trades tool to fetch and filter recent Polymarket trades (free Data API), optionally by market or wallet.
page-driven-development
Review and write React/Next.js code following Page Driven Development principles. Use when organizing components, making file structure decisions, or asked to "review structure", "organize code", "refactor components", or "follow PDD".
skill-consolidator
Create and maintain first-party custom skills by strategically consolidating overlapping third-party skills. Scans globally installed skills (prefer ~/.agents/skills, or $CODEX_HOME/skills, or ~/.codex/skills) to produce an overlap report, then guides merging into a smaller, linked set inside this repo’s `skills/` directory. Use when asked to "clean up skills", "merge skills", "remove duplicates", "consolidate overlapping skills", "organize my skills", or "create a custom skill from other skills".
workflow-visualizer
Map any system or workflow as a beautiful interactive HTML diagram
agents-reminder
Reminds the agent to refresh on AGENTS.md guidelines before proceeding with tasks. Use at the start of a session or when unsure about agent policies.
conventional-commits
Generates git commit messages following Conventional Commits 1.0.0 specification with semantic types (feat, fix, etc.), optional scope, and breaking change annotations. Use when committing code changes or creating commit messages.
playwright
Canonical Playwright hub for E2E tests and ad-hoc browser automation. Use when the user explicitly mentions "Playwright", "@playwright/test", "npx playwright", "playwright.config.ts", "PWDEBUG", "trace viewer", or "toHaveScreenshot". Avoid using for generic browser automation unless Playwright is requested, and avoid using for pure web scraping.
project-status-phase
Choose the next GitHub project-board item to work on and move or delegate it through the next truthful phase using board rules, repo state, linked PRs, and docs. Use when asked to move, triage, reclassify, pick the next item, or work a board phase by phase.
serp-toc
Route SERP org questions to the right repo, docs, and local clone quickly. Use when Codex needs to figure out where to look first across the SERP org, including repo lookup, server or infrastructure questions, secrets or env questions, branch orientation, local path discovery, or deciding whether something belongs in the docs hub versus an owning repo.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
auth-flow
Claude Code authentication in headless Daytona sandboxes. Use when implementing AuthManager, setup wizard, credential validation, or handling OAuth token/API key injection.
claude-code-cli
Claude Code CLI usage for automated/headless execution in Daytona sandboxes. Use when running Claude Code commands, configuring authentication, or setting up non-interactive mode.
electron-ipc
Electron IPC communication patterns between main and renderer processes. Use when implementing IPC handlers, sending events between processes, or working with the preload script.
daytona-integration
Daytona SDK integration for sandbox lifecycle management. Use when working with SandboxManager, creating/destroying sandboxes, executing commands in sandboxes, or transferring files between sandboxes and local filesystem.
database-schema
SQLite database schema and operations using better-sqlite3. Use when working with StateManager, persisting runs/rounds/agents, or querying run history.
terminal-streaming
xterm.js terminal integration for streaming agent output. Use when implementing AgentCard terminal display, configuring xterm addons, or handling real-time output streaming.
cloud-run-quickstart
Get started deploying applications to Google Cloud Run. Use when a user wants to deploy their app, share their app by deploying to a cloud service, make their app accessible on the internet, or needs help choosing between Cloud Run deployment methods (no-build, buildpacks, Dockerfile, or container image).
github-spec-kit
Expert guidance for Spec-Driven Development using the GitHub Spec Kit. Use when the user wants to initialize a project, create specifications, plan implementations, or execute tasks based on the Spec Kit workflow. Triggers on "spec kit", "specify", "create spec", "spec-driven development".
spec
>
project-status-report
Create and update structured project status reports from meetings, messages, documents, or notes. Use when users need to extract status updates into markdown reports with summary, problems, risks, and actions sections, consolidate multiple team reports, update existing reports maintaining reverse chronological order, save/modify reports in Obsidian vault, or mention terms like "status report", "project update", "sync", "war room", "team report", or "weekly update".
remove-ai-comments
Removes redundant, obvious, or "AI-flavored" comments from code to improve signal-to-noise ratio. Use when the user asks to "clean up comments", "remove AI comments", or makes a general request to refactor verbose code documentation.
skill-create
Instructions for AI agents to create new skills and add them to the skills repository
supabase-workflow
Supabase database migrations, type generation, edge function management, and best practices for this project
bun-elysia
Build full-stack applications with Bun.js and Elysia.js. Use this skill when working with Bun runtime, Bun native APIs (SQL databases, Redis, S3), Bun workspaces/monorepos, Elysia.js web framework, or migrating from Fastify to Elysia. Covers setup, routing, validation, authentication, WebSocket, and end-to-end type safety with Eden.
skill-pdf-to-pptx-tool
Convert PDF to PowerPoint presentations
pydantic-ai-agent
Build production-grade Pydantic AI agents with layered architecture. Use when creating AI agents with tool systems, dependency injection, streaming responses, multi-provider support, or conversation state management. Includes scaffolding scripts for rapid project setup and comprehensive architectural patterns for FastAPI web services and CLI applications.
investigate
Investigate Problem - analyzes a problem in the codebase and proposes actionable solutions
spec:test
Execute Tests - walks through test cases from the test plan, collects results, and updates the plan. Use when verifying a feature implementation.
spec:test-plan
Test Plan - creates a manual test plan with traceable test cases from specification documents. Use when preparing to verify a feature implementation.
spec:tasks
Task Breakdown - generates an implementation plan with tracked tasks based on requirements and design documents. Use when breaking down a design into actionable work items.
spec:status
Spec Status - displays pipeline progress dashboard for a single specification showing document statuses, blockers, and next action.
spec:review
Review Specification - validates documents for completeness, quality, and consistency against the codebase. Use when checking spec quality at any pipeline stage.
spec:research
Technical Research - investigates codebase and explores solution alternatives based on requirements. Use when choosing between implementation approaches.
spec:requirements
Requirements Analysis - gathers requirements through structured questions and produces a requirements document with testable acceptance criteria. Use when starting a new feature spec or documenting requirements.
Page 1402 of 1487 · 74334 results
