Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Open-source Claude Code skills and Codex skills for AI-first work. Audit, re-engineer, and bootstrap projects with AI-first design principles.
SkillMIT★ 134No key
A specialist team for the coding agent you already use: 12 roles, 21 workflows and 33 skills that plan, build in parallel, review and debug, leaving plans, ADRs and results as files. Gates wait for yo
SkillMIT★ 1.3kNo key
Hermes-first agent skill that turns long videos into captioned, viral-ready social clips — local engine, agent does the editorial.
SkillMIT★ 9No key
Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience, and when configuring an
OfficialSkillMIT★ 485 in collectionNo key
Open-source client + docs for FrameFetch — any social-video URL to transcript, metadata & frames. Agent-first API + MCP, pay with x402 (USDC).
Hosted by authorMITFew starsNo key
Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed on-device into markdown you own.
SkillMIT★ 1.6kNo key
Agent-first short-form AI video generation CLI and MCP server for Sora, Veo, xAI and Seedance
Node.jsMIT★ 2Few starsNo key
Open, agent-native CAD; edit code, not click menus, make things. kernelCAD.com
Node.jsMIT★ 32No key
Take your script to the screen. Agent-first storyboard & AI film production toolkit — Skill/MCP/CLI for Claude Code, Codex, OpenCode. GPT-image-2 + Seedance 2.x/Minimax H3.
SkillMIT★ 4Few starsNo key
Agent-first local CLI for cleaning and enhancing talking-head videos with transcripts, reviewable edit plans, captions, visual assets, music, HyperFrames rendering, and artifact inspection.
SkillMIT★ 4Few starsNo key
An agent skill for generating controllable construction-process video prompts with first/last-frame constraints.
SkillMIT★ 5No key
This is a frontend design skill specifically tailored for the Codex and GPT-5.6 series models, aiming to enhance the frontend design capabilities of the GPT series models. Through a customized GPT ima
SkillMIT★ 6No key
Design, evaluate, and ship agent skills. The Skill Bundle is the durable asset; SKILL.md is an output.
SkillMIT★ 2Few starsNo key
Local-first, open-source alternative to Anthropic's Claude Design. MIT-licensed, BYO agent CLI — Claude Code, Kimi, Codex, or any SDK-compatible model. Composable skills · three edit paths · designs a
SkillMIT★ 11No key
A design agent for Figma. A plugin for Claude Code: seven skills so the agent works in your file from your components and variables, makes presentations, and writes text that doesn't read as generated
SkillMIT★ 4Few starsNo key
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
SkillMIT★ 145kNo key
Document analysis with inline source screenshots. When you ask Copilot to analyze a document, Eyeball generates a Word doc where every factual claim includes a highlighted screenshot from the source m
OfficialSkillMIT★ 40k in collectionNo key
Design AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only; excludes implementation and general code review.
OfficialSkillMIT★ 40k in collectionNo key
Agent-first CLI for Figma: read designs, resolve design tokens, render screenshots, and export assets from the shell
SkillMIT★ 1Few starsNo key
ComfyUI Development Skills is a portable Agent Skills pack for people who develop ComfyUI itself, custom nodes, frontend extensions, workflows, integrations, tests, and related tooling.
SkillMIT★ 4Few starsNo key
Creates the Tamagui brand system for an Expo/React Native Power Apps mobile app, including design-system.md, tokens.ts, and an HTML gallery.
OfficialSkillMIT★ 1.0k in collectionNo key
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwri
OfficialSkillMIT★ 143k in collectionNo key
Spin up a personal, motivating daily focus board that renders in a browser canvas and that the user drives by talking to their AI partner. Tasks track status (to-do → in progress → done) with timestam
OfficialSkillMIT★ 40k in collectionNo key
Who stands behind it