Agent Skills Hub

tavily-web

Advanced web search, content extraction, and site crawling capabilities using the Tavily API, optimized for AI agent research and data gathering.

browser-use

AI-powered browser automation server for web interaction, data extraction, and research using the Model Context Protocol.

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.

chrome-devtools-mcp-manager

Manage OpenClaw's built-in Chrome browser and chrome-devtools-mcp integration for robust browser automation using the Model Context Protocol.

prompt-improver

Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.

calorie-detective-v2-0-0

AI-powered food calorie and nutrient calculator. Uses vision recognition to identify meals, calculate macronutrients, and provide health suggestions based on a built-in nutrition database.

instagram-poster

Automate Instagram posts via Telegram or CLI. Features residential proxy bypass, session caching, and WaveSpeed image integration.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

anki-connect-skill

Manage your Anki flashcards effortlessly via the AnkiConnect REST API. Create, update, search, and organize decks, notes, and cards directly through your AI agent.

zai-cli

Execute z.AI CLI for multimodal analysis, web search, reader, and GitHub repo exploration via CLI and MCP.

frontend-design-pro

Build $50k-grade frontend interfaces with production-ready code, professional typography, and high-fidelity image integration.

session-investigator

Analyze and debug fast-agent session histories, tool execution logs, and conversation timing to resolve performance bottlenecks, tool loops, and unexpected session terminations.