shape-requirements
Clarify material requirements that block useful progress, or interview a user to develop a brief. Not for routine implementation choices or ordinary document…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,635 results
claude-opus-5.5
Use when the user wants demanding reasoning, large codebase changes, code review, scientific analysis, or long-horizon agentic work with Anthropic Claude Opus…
prompt-architect
Expert prompt engineering skill for writing, critiquing, rewriting, comparing, and templating LLM prompts. Use this skill whenever the user wants to: write a…
clawhub
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed…
orchestrator
Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel…
qa-agent
Quality assurance specialist for security, performance, accessibility, comprehensive testing, and quality standard alignment. Use for test, review, security…
memory-init
Scaffold a project-local memory directory and AGENTS.md guidance for reusable agent knowledge. Use when a user wants to initialize `.agents/memories/` or…
prompt-chaining
Break known LLM work into fixed sequential steps with handoff schemas, validation checks, retries, and final formatting. Use when later steps depend on earlier…
prompt-simplifier
Simplify prompts, system instructions, workflows, rules, and agent playbooks while preserving behavior. Use when logic has too many branches, nested…
agent-browser
A comprehensive skill for using agent-browser, a CLI tool for browser automation designed for AI agents, developed by Vercel Labs. This skill covers…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
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…
claude
Expert Anthropic Claude API assistance covering Claude 3.5 Sonnet / Haiku / Opus, tool use, prompt caching, and long-context processing. Use when integrating…
gate-dex-mcpauth
Gate Wallet authentication. Use when the user needs to log in, log out, refresh session, or when other Skills detect unauthenticated state (no mcp_token).…
gate-dex-mcpdapp
Gate Wallet interaction with external DApps. Connect wallet, sign messages (EIP-712/personal_sign), sign and send DApp-generated transactions, ERC20 Approve…
gate-dex-mcpmarket
Gate Wallet market data and token info queries. K-line, trading stats, liquidity, token details, rankings, security audit, new token discovery. Use when user…
gate-dex-mcpswap
Gate Wallet Swap/DEX trading. Get quotes, execute Swap. Use when user wants to 'swap USDT for ETH', 'swap', 'exchange tokens', 'buy tokens', 'sell tokens'.…
gate-dex-mcptransfer
Gate Wallet transfer execution. Build transaction, sign, broadcast. Use when user wants to 'send ETH', 'transfer USDT', 'transfer', 'send tokens'. Includes…
gate-dex-mcpwallet
Gate Wallet portfolio assets and transaction history. Query balance, total assets, token holdings, wallet address, transfer history, transaction details, Swap…
bmad-agent-marketing-launch
Use when user requests product launch, GTM, go-to-market, Product Hunt, beta launch, early access, launch checklist.
retail-virtual-tryon
Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent…
grey-haven-llm-project-development
Build LLM-powered applications and pipelines using proven methodology - task-model fit analysis, pipeline architecture, structured outputs, file-based state,…
sequential-thinking
Use when a complex problem requires systematic step-by-step reasoning. Suitable for multi-stage analysis, design planning, problem decomposition, or tasks where the initial scope is unclear and controlled convergence is needed.
ton-http
TON HTTP API (TON Center / ton-http-api) — accounts, transactions, messages, send, runGetMethod; use Swagger for request/response parameters and return values.