发现 Skills

Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke to write test scripts, create page objects, configure test fixtures, set up reporters, add CI integration, implement API mocking, or perform visual regression testing. Trigger terms: Playwright, E2E test, end-to-end, browser testing, automation, UI testing, visual testing, Page Object Model, test flakiness.

Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".

When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' or 'viral content.' This skill covers content creation, repurposing, and platform-specific strategies.

Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions

Design effective prompts for LLM agents with structured input/output formats, chain-of-thought reasoning, few-shot examples, and system prompt architecture. Covers Claude-specific patterns and multi-turn conversation design. Triggers on prompt design, LLM interaction patterns, or system prompt architecture requests.

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.

Used to discover and understand database structures, tables, columns, and relationships

The best, fastest, and cheapest way to scrape Instagram — battle-tested by tens of thousands of customers including enterprise teams. Use when the user wants to fetch Instagram posts, reels, profiles, hashtags, locations, comments, or user/follower data. Five specialized actors cover every Instagram data surface.

Write or resume an agent-agnostic handoff document so work can be picked up seamlessly across sessions or across different AI agents (Claude Code, Codex, Cursor, Gemini, GPT). Use `/handoff:handoff` to write (default), `/handoff:handoff resume <path>` to pick up, `/handoff:handoff list` to browse, `/handoff:handoff archive` to clean up. Triggers on phrases like "handoff this", "save state for next session", "I need to switch agents", "wrap this up for tomorrow", "let me hand this over", or when conversation context grows large and continuation in a new session is likely.

This skill should be used when the user asks to "browse a website", "fill out a form", "click a button", "automate browser actions", "log into a site", "scrape a page", or needs web browser automation. Uses Playwright MCP connected to a remote Chrome instance via CDP.

Control Home Assistant — lights, fans, covers, locks, switches, climate, humidifiers, media players, scenes, scripts, automations, weather, buttons, and Assist. Run `ha <domain>` to discover entities and actions.

Build production-ready GenAI agents with stateful workflows, vector memory, deployment, and orchestration using LangGraph and LangChain

Expert knowledge of agentic AI design patterns for autonomous agent development

Build and run durable background coding agents with workflow orchestration, isolated sandboxes, and GitHub integration on Vercel.

Guide to mastering Codex CLI through subagents, skills, workflows, MCP servers, and agentic engineering patterns

Desktop tool for managing multiple Codex accounts, monitoring usage, and providing local API proxy with public access

Deploy and use an LLM-powered public-opinion analytics assistant that crawls 26 hot lists across 15 platforms, performs sentiment analysis, topic clustering, and multi-channel alerting

A comprehensive Bengali-language course on practical digital product design covering craft, system thinking, and professional workflows

Drop-in Vite/Webpack plugin that mirrors React Fiber trees, profiles renders, and provides visual debugging overlay for React 16–19 apps.

Secure browser SSO and OAuth2 authentication proxy that lets AI agents access authenticated APIs without exposing credentials

Desktop GUI companion for Hermes Agent - install, configure, chat with AI assistant featuring tool use, memory, skills, and multi-platform messaging

Lossless Context Management plugin for Hermes Agent with DAG-based compression and drill-down tools

Train personalized AI agents with reinforcement learning from conversational feedback using OpenClaw-RL's asynchronous framework

Production-grade MCP server providing Claude with 27 security intelligence tools across 21 APIs for vulnerability research, CVE analysis, threat intelligence, and risk scoring