技能库 3997 个

Expose the Teller delta-neutral + lending Model Context Protocol server. Use this when you need to install, run, or upda

Expose the Teller delta-neutral + lending Model Context Protocol server. Use this when you need to install, run, or upda

Expose the Teller delta-neutral + lending Model Context Protocol server. Use this when you need to install, run, or upda

Join a high-stakes collaborative knowledge exchange. Connect your agent to answer human questions, vote on peers, and ea

Play Clawing Trap - an AI social deduction game where 10 agents compete to identify the imposter. Use when the user want

Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screensh

Upload images to img402.dev and get a public URL. Free tier: 1MB max, 7-day retention, no auth. Use when the agent needs

Intelligent caching with LRU/LFU strategies and TTL management

Advanced rate limiting with tiered controls and quota management

GPT-specific pattern detection with model fingerprinting and version identification

Browse, search, and download ebooks from OPDS catalogs using the opdscli CLI. Use when adding/managing catalogs, searchi

Orchestrate the Life Control CLI skill for OpenClaw agent fleets: initialize the Life Control database, register agent p

Semantic quote search with source transparency. Find quotes by meaning, not keywords.

Generate professional portrait photography using Google Imagen 3. Use when creating realistic portraits, headshots, or a

Manage EffortList AI folders, tasks, and todos. Use when the user wants to organize their life, track projects, or manag

Vision-driven iOS device automation using Midscene CLI. Operates entirely from screenshots — no DOM or accessibility lab

Query Idealista API via idealista-cli (OAuth2 client credentials).

Vision-driven browser automation using Midscene. Operates entirely from screenshots — no DOM or accessibility labels req

Vision-driven desktop automation using Midscene. Control your desktop (macOS, Windows, Linux) with natural language comm

Vision-driven Android device automation using Midscene. Operates entirely from screenshots — no DOM or accessibility lab