Loading...
Loading...
Found 11,818 Skills
The Meta-Skill. Use this to create NEW skills (tools) for the agent.
Analyzes and improves LLM prompts and agent instructions for token efficiency, determinism, and clarity. Use when (1) writing a new system prompt, skill, or CLAUDE.md file, (2) reviewing or improving an existing prompt for clarity and efficiency, (3) diagnosing why a prompt produces inconsistent or unexpected results, (4) converting natural language instructions into imperative LLM directives, or (5) evaluating prompt anti-patterns and suggesting fixes. Applies to all LLM platforms (Claude, GPT, Gemini, Llama).
Get external agent review and feedback. Routes Anthropic models through Claude Agent SDK (uses local subscription) and other models through OpenRouter API. Use for code review, architecture feedback, or any external consultation.
Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
Use for Cobo Agentic Wallet operations via the `caw` CLI: wallet onboarding, token transfers (USDC, USDT, ETH, SOL, etc.), smart contract calls, balance queries, and policy denial handling. Covers DeFi execution on EVM (Base, Ethereum, Arbitrum, Optimism, Polygon) and Solana: Uniswap V3 swaps, Aave V3 lending, Jupiter swaps, DCA, grid trading, Polymarket, and Drift perps. Use when: user mentions caw, cobo-agentic-wallet, MPC wallet, TSS node, Cobo Portal, agent wallet, or needs any crypto wallet operation — even without explicit "Cobo" mention. NOT for: fiat payments, bank transfers, or crypto-to-fiat off-ramp.
Generates comprehensive, workable unit tests for any programming language using a multi-agent pipeline. Use when asked to generate tests, write unit tests, improve test coverage, add test coverage, create test files, or test a codebase. Supports C#, TypeScript, JavaScript, Python, Go, Rust, Java, and more. Orchestrates research, planning, and implementation phases to produce tests that compile, pass, and follow project conventions.
Unified payment dispatcher covering x402 (`exact` / `aggr_deferred` schemes), MPP (`charge` / `session` intents), and a2a-pay (`a2a_charge` paymentId flow). Detects HTTP 402 protocol from response headers and routes to the matching scheme/intent reference; also handles a2a paymentId mentions without a 402. Loads `references/exact.md` (x402 exact scheme — full EIP-3009 TEE or local-key fallback), `references/aggr_deferred.md` (x402 aggr_deferred scheme — Session Key Ed25519 with sessionCert), `references/charge.md` (MPP one-shot charge in transaction or hash mode, with splits), `references/session.md` (MPP channel: open + voucher loop + topUp + close, with state echo), or `references/a2a_charge.md` (a2a-pay create / pay / auto-poll status). Returns a ready-to-paste authorization header (x402 / MPP) or a tx-hash + status (a2a). Trigger words (English): '402', 'payment required', 'mpp', 'machine payment', 'pay for access', 'payment-gated', 'WWW-Authenticate: Payment', 'x402', 'x402Version', 'PAYMENT-REQUIRED', 'PAYMENT-SIGNATURE', 'X-PAYMENT', 'open channel', 'voucher', 'session payment', 'close channel', 'topup channel', 'top up channel', 'settle channel', 'settle session', 'refund channel', 'channelId', 'channel_id', 'paymentId', 'a2a_', 'a2a payment', 'create payment link', 'payment link', 'payment status'. Trigger words (Chinese): '支付通道', '关闭通道', '关闭会话', '关闭支付通道', '充值通道', '续费通道', '结算通道', '结算会话', '关单', '凭证', '会话支付', '付款链接', '创建支付', '支付状态'. Critical sensitivity rule: any user mention of close / topup / settle / voucher / refund near a `channel_id`, `0x...` channel hash, or 'session' / 'channel' context = MPP mid-session operation — load this skill, jump into `references/session.md`, do NOT search for a separate close/topup tool.
Delete specific observations or sessions from agentmemory. Use when user says "forget this", "delete memory", or wants to remove specific data for privacy.
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model evaluations.
Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear, or when answering what agentmemory can do via MCP.
Overview of the Neon platform for apps and agents, spanning Postgres, Auth, Data API, and the new services: Object Storage, Compute Functions, and AI Gateway. Use whenever "Neon" is mentioned for an overview of how to work with Neon and how to get started. Otherwise, the individual capabilities are the triggers: "object storage" or "S3-compatible storage", "serverless functions", "background jobs", or "run code near my database", "AI gateway", "LLM proxy", "model routing", or "call an LLM" → AI Gateway; "database", "Postgres", or "authentication" → Postgres and Auth.