The Tool Hunt
● Updated daily · 201 graded resources

The leaderboard for AI skills, agents & MCP servers.

Everything you need to build with AI. Find it, test it, use it. We scan GitHub every day and grade each project on license, quality and upkeep — in simple English.

⌕
$ npx skills add anthropics/skills

WORKS WITH

// LEADERBOARD

What builders should look at first

1EgoAlpha logoprompt-in-context-learningEgoAlpha/prompt-in-context-learning · Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates. 2decocms logostudiodecocms/studio · Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar3oxbshw logoOpen-Workflow-Libraryoxbshw/Open-Workflow-Library · Open workflow intelligence for discovering, validating, repairing, and generating automation workflows across frameworks — starting with n8n.4SFKislev logoFlueSFKislev/Flue · Let agents control many desktop software directly from the cli, with one pip install, and no MCP servers.5umputun logorevdiffumputun/revdiff · TUI for reviewing diffs, files, and documents with inline annotations6aviaviavi logocelorgaaviaviavi/celorga · A local-first workspace for your life, work, and AI agents. Built around plain-text Org files you own.7HazAT logoultimateHazAT/ultimate · A local coding agent with a web UI that builds itself while it runs, on Pi Durable8NVIDIA logohalos-outside-in-safetyNVIDIA/halos-outside-in-safety · NVIDIA Halos Outside-In Safety Blueprint extends robot perception beyond on-board sensors by using external infrastructure cameras and AI agents to dynamically control robot behavior and perform at maximum efficiency. 9jamditis logoclaude-skills-journalismjamditis/claude-skills-journalism · Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more10ReflexioAI logoreflexioReflexioAI/reflexio · Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions. 11strands-agents logoboxstrands-agents/box · Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support planned.12NotASithLord logopeerdNotASithLord/peerd · The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK, no backend, no telemetry.

L = License · Q = Quality · M = Maintenance, graded A–D. Stars come from GitHub. Score = our 100-point radar score.

See the full library →

Browse by type

Pro: every house-made skill and workflow, plus early access.

$22.99/year (Save 40%) or $3.29/month. 7-day refund on your first purchase.