The open hub for AI agent builders.
Production-ready skills, tools, MCP servers, and real examples for Grok Build, Claude, Cursor, and more.
Featured Skills
Performs deep, structured code reviews covering correctness, security, performance, maintainability, and testing gaps. Outputs actionable patches and prioritized findings.
Audits code and configuration for vulnerabilities: injection, broken auth, secrets, dependency risks, and insecure defaults. Reports severity-ranked findings with fixes.
Finds and fixes real performance problems: N+1 queries, unnecessary renders, slow hot paths, and memory growth. Measures before and after — no cargo-cult optimization.
Writes comprehensive, maintainable unit, integration, and property-based tests. Focuses on high-value coverage and realistic edge cases.
Systematically diagnoses bugs and production issues. Reproduces the problem, narrows the root cause, and proposes minimal fixes with explanations.
Safely performs coordinated refactors across many files while preserving behavior. Produces a step-by-step plan + the exact edits.
Designs clean, evolvable APIs (REST, GraphQL, or RPC). Produces OpenAPI specs, client code, error models, and migration guides.
Upgrades dependencies safely: reads changelogs, identifies breaking changes, migrates code, and verifies with the test suite — one risk group at a time.
Useful Tools
Anthropic's agentic coding CLI. Reads your repo, edits files, runs commands, and ships features end-to-end from the terminal. Supports skills, MCP servers, hooks, and subagents.
OpenAI's open-source coding agent for the terminal. Plans, edits, and runs code in a sandbox with configurable approval modes. Reads AGENTS.md natively.
xAI's terminal coding agent. Plan Mode writes a file-by-file plan before editing, runs up to 8 parallel subagents in isolated git worktrees, and has native MCP support. Reads AGENTS.md and runs headless in CI. Powered by grok-build-0.1.
Open-source terminal coding agent for the Grok API, with live X and web search built in and MCP server support. A lightweight, BYO-API-key alternative to the official Grok Build.
Google's open-source terminal agent powered by Gemini. Large context window, built-in web search grounding, and MCP support. Generous free tier.
Pioneering terminal-based AI pair programmer. Works directly in your repo with tight Git integration, multi-file edits, and support for many model providers.
Open-source terminal coding agent with a polished TUI. Provider-agnostic — bring Claude, GPT, Gemini, or local models — with an LSP-powered understanding of your code.
Block's open-source AI agent for engineering tasks. Runs locally as a CLI or desktop app, works with any LLM provider, and is built around MCP extensions.
MCP Servers
Reference filesystem access for agents. Read, write, list, move, and search files within explicitly allowed directories.
GitHub's official MCP server. Manage issues, PRs, branches, workflows, and code scanning — or just let the agent read your repos.
Reference Git server. Status, diff, log, branch, commit, and search — structured Git operations for repos the agent works in.
Supabase's official server. Query the database, apply migrations, manage config, fetch logs, and generate TypeScript types from your agent.
Sentry's hosted MCP server. Pull real production errors, stack traces, and issue context straight into your debugging session.
Notion's official server. Search, read, and write pages and databases — give your agent access to the team's actual docs and specs.
Web scraping built for LLMs: turn any site into clean markdown, crawl whole domains, search, and extract structured data.
Microsoft's official browser automation server. Navigate pages, click, fill forms, take screenshots, and read pages via fast accessibility snapshots.
High-Quality Examples
A production-grade AGENTS.md used by real teams. Covers principles, skills, workflows, and review standards.
A complete, production-ready skill definition you can download and use.
A complete multi-step workflow used for feature development with agents.
The exact format high-performing teams use to hand work from planning agent to implementation agent.
A powerful pattern that dramatically improves output quality. Use after any major artifact.
Practical strategy for giving agents enough context without blowing the context window.