init
3649Skill Claude CodeCodex
Scaffold a new Pipecat project with guided setup.
23,553 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 233LLM 217agent 200agents 151skills 145agentic-workflow 110agent-orchestration 86openai 86antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 63
Skill Claude CodeCodex
Scaffold a new Pipecat project with guided setup.
Skill Claude CodeCodex
A guide for connecting an AI agent to agent-node, a network of computers that lets agents work together. It describes using other computers' coding agents, moving files between computers, chatting, and running remote commands.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Write descriptions that help AI agents understand what each tool does, what prerequisites it has, and how it relates to other tools. A good description answers.
Skill Claude CodeCodex
Delegate work across the AI coding CLIs the user already has installed, through the local AgentBridge MCP server. Invoked as /agentbridge — bare with a goal to run a build, or with a subcommand: setup, status, doctor, profile, recon, review, resume. Use when the user types /agentbridge, or asks to set up, inspect or…
ustc-fyk/antigravity-codex-mcp
Skill Claude CodeCodex
Dynamically enable and orchestrate Antigravity CLI (AGY) for the current Codex project only when the user explicitly asks to load or use AGY/Antigravity. Manage exact project read authorization, active conversations, delegation, transcript synchronization, isolated implementation, audit records, and revocation.
Skill Claude CodeCodex
A set of Chinese-language instructions for using an MCP server, a program that gives an agent access to defined tools or data. It covers the tools named think, contextualsearch, and auditedrun.
Skill Claude CodeCodex
Route work through an MCP gateway with token-efficient downstream service discovery, filtered tool search, exact schema lookup, service diagnostics, and forwarded tool calls. Use when an agent needs to find or call tools behind the gateway without loading every downstream schema.
Skill Claude CodeCodex
Comprehensive MCP Server Skill combining base development guidance with enterprise packaging best practices (security, observability, CI/CD, Kubernetes, network, compliance). Use for building MCP servers in Python (FastMCP) or TypeScript with production readiness.
Skill Claude CodeCodex
MCP server exposing OpenClaw tools (smart home, memory, cron, sub-agent orchestration) to Claude Desktop, Cursor, Windsurf, and any MCP client. Includes Gemini, Codex, and local LLM sub-agents plus smart prompt splitting.
Skill Claude CodeCodex
Enable when the task is new/greenfield, vague, or missing stack/scope/IO/path. Default is ASK, not skip. Read repo first (grep/read only). Ask ONE detailed question per turn (why + 2–4 options) until checkreadiness ready=true. Do NOT assume defaults (Vue3/Express/JWT). Log to adhd/sessions/.md.
Skill Claude CodeCodex
Autonomous MCP server routing, multiplexing, performance benchmarking, and real-time observability suite for AI coding agents.
Skill Claude CodeCodex
One-click security audit for your MCP setup. Get a safety score, plain-English explanations, and fix recommendations.
muanlin/agent-collaboration-orchestrator
Skill Claude CodeCodex
Run a TRAE-led collaborative coding workflow where TRAE desktop or mobile starts project work, tracks progress, adjusts or cancels tasks, views artifacts, and delegates difficult implementation subtasks to Codex through the agent-collaboration-orchestrator MCP bridge. Use when the user mentions TRAE, Codex…
Skill Claude CodeCodex
Coordinate with other AI agents over technocore.chat - shared rooms, durable notes, long-polling, and Ed25519 signed identity. Use when you need to leave a message for another agent, wait for one, persist state across your own sessions, or publish a verifiable feed other agents can consume.
Skill Claude CodeCodex
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
Skill Claude CodeCodex
Delegate a scoped local coding, analysis, review, or testing subtask to a user-selected Cursor model through cursor-relay-mcp. Use when the user explicitly asks to call Cursor, use a Cursor model as a subtask, or requests Cursor Relay. Keep destructive actions and final decisions with the calling agent.
Skill Claude CodeCodex
Universal autonomous long-term memory for AI agents. Remember everything, send only what matters.
vkolotov/mcp-agent-collaboration
Skill Claude CodeCodex
Use when collaborating with other agents through the MCP Agent Collaboration server.
Skill Claude Code
A guide for creating an MCP app, including what MCP apps are, their technology stack, folder layout, and common setup problems. MCP is a way for AI assistants to use external tools and data.
NimbleBrainInc/mcp-registry-tools
Skill Claude CodeCodex
Skill "mcp_registry_tools" from NimbleBrainInc/mcp-registry-tools, covering registry tools, tool selection, multi-step workflows, find and inspect an mcp server and key patterns.
Skill Claude CodeCodex
Run the shared agent room. Use when the user says "recruit", addresses someone with "@name", asks to "ask the team", wants a "second opinion", says "have them discuss" / "let the team debate" / "thrash this out", asks you to "hire"/"find me a"/"recruit the best" model or role for a job, wants to see or edit a…
Skill Claude CodeCodex
This skill enables your OpenClaw agent to act as a real-time supervisor for Claude Code sessions.
sat0ps/mcp-server-azure-platform
Skill Claude CodeCodex
Skills are repeatable procedures for AI agents. Each skill defines a deterministic path to the correct outcome.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: