multi-agent-coordinator
Use to coordinate several long-running workers with durable prompts, event-driven watches, review gates, owner updates, and safe cleanup.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,653 results
unattended-agent-runs
Use to design or operate recurring newsroom agent work without a person watching each run. Covers a simple process-per-run starter and a persistent supervised…
jd-aipay-onboarding
JD AI Pay one-stop integration Agent. Use this skill whenever the user wants to 接入/集成/联调/上线 京东AI付, says 让AI帮我接入AI付, mentions jdpay-aipay, AI付快速接入, 一站式接入, 沙箱联调, 生产配置替换, 上线验证, 产品开通,…
klisk-guide
Guide for building AI agents programmatically using the Klisk CLI and framework. Use when the user asks to create an AI agent. Klisk is the easiest way to…
llm-wiki
Build a persistent compounding wiki from raw sources using the LLM Wiki pattern
project-kickoff
Bootstrap new projects with curated settings.local.json permissions, CLAUDE.md, and .gitignore. Detects project type (cloudflare-worker, vercel-app,…
rule-setup
Install categorized agent workflow conventions and optional Cursor subagent model enforcement into a project. Explicit invocation only.
generative-optimization
A skill on generative optimization for using Gaussian Mixture Models and Conditional Flow matching models for optimization tasks.
skill-cleaner
Audit Joel's Pi/joelclaw skills: loaded roots, duplicates, stale or unused skills, prompt-budget cost, and compact descriptions. Use when trimming skill prompt…
mcp-setup
Configure and troubleshoot MCP servers in Claude Code. Quick reference for installing, verifying, and debugging MCP connections (Slack, Sentry, PostHog, Figma,…
lore
Use to recall anything from past agent sessions with the server-free `lore` CLI — the "what did we decide", "how did we build X", "why did we drop Y", "find…
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
autonomous-agent-patterns
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use…
claude code guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best…
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI…
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…
prompt-engineering
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies,…
mcp-vstash
MCP server integration for vstash document memory. Use when configuring Claude Desktop or other MCP-compatible AI assistants with persistent document memory,…
ralph
Autonomous agent loop for completing features. Use when asked to 'use ralph', 'ralph this', or to autonomously implement a feature end-to-end. Creates prd.json…
jr-rails-second-opinion
Get a Rails-flavored second opinion on a branch, PR, or working tree by delegating to a locally-installed agentic CLI (claude, codex, opencode, gemini, aider,…
context7-mcp
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code…
latency-quality-tradeoff-optimizer
Compare model, decoding, caching, and routing choices against quality, latency, and cost. Use when a system must be practical, not just accurate.
rag-diagnostics-analyst
Diagnose whether failures come from retrieval, context selection, grounding, or generation in a RAG system. Use when a retrieval-augmented system underperforms.