MCP servers and skills: search, filter by where they run, and compare.
One agent proves a capability is safe. Every other agent — Codex, Cursor, Claude Code — reuses it instantly, without rebuilding or re-verifying.
SkillMIT★ 4Few starsNo key
Claude Code Workflow for beginners & intermediate users. Tutorial and Installer included
SkillMIT★ 1.4kNo key
Build production-grade agents with OpenAI AgentKit, a no-code platfrom.
SkillMIT★ 233No key
Phase-based AI development framework for AI Coding Agents. 17 specialized agents across 6 phases, handing off through files in your repo — and it reads the codebase you already have.
SkillMIT★ 29No key
mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insights-style HTML report on how you work: what you build, wher
SkillMIT★ 85No key
Transform Claude Code sessions into engaging, educational blog posts with intelligent narrative chunking and PII redaction
Node.jsMIT★ 3Few starsNo key
A personal voice agent you can phone: OpenAI Realtime for the conversation, Claude Agent SDK subagents for the work.
SkillApache-2.0★ 2Few starsNo key
A free, open-source suite of website skills: instructions your AI coding assistant follows to build and test a site you own, so people find it on Google and in AI answers.
SkillMIT★ 8No key
Local dashboard to switch the active Claude Code account with one click, showing each account's 5-hour and weekly quota. Zero dependencies, host and WSL, Docker-ready.
SkillMIT★ 4Few starsNo key
Auto-summarize Claude Code sessions as local markdown — session summaries, keyword index, on-demand reports.
GoGPL-3.0★ 38No key
Universal AI agent skill that turns any material into learning-science-based self-study courses with retrieval practice, spaced repetition, and tutor mode.
SkillMIT★ 25No key
Claude Code skill: weekly work reports from local session transcripts + GitHub PRs, as Markdown or a self-contained HTML deck.
SkillMIT★ 6No key
AI usage and cost in your macOS menu bar: live rate limits for Claude, OpenAI and Gemini, ccusage-style costs from local logs, MCP server for model routing
SkillMIT★ 3Few starsNo key
Claude Agent Skill that turns any data into a self-contained HTML dashboard or report with interactive SVG charts. Zero dependencies, works offline. Claude Code plugin.
SkillMIT★ 3Few starsNo key
Give your AI agent a social media brain: TikTok, YouTube Shorts & Instagram Reels trends, viral video analysis, creators, sounds & hashtags. MCP server + skills for Claude Code, Cursor, Codex.
SkillMIT★ 3Few starsNo key
Find the security holes your AI left behind. Zero-config scanner for apps built with Cursor, Claude Code, Lovable & Copilot: leaked keys, open Supabase/Firebase data, missing auth, SQL injection and m
SkillMIT★ 2Few starsNo key
An HP bar for Claude Code and Codex accounts. CLI, agent skill and macOS menu bar app for usage limits and resets.
SkillMITFew starsNo key
Build AI software architecture with 6 specialist agents, 15 modes, and parallel planning from idea to infrastructure
PythonMITFew starsNo key
Agent skills for Claude Code and Codex that do the weekly shop on nemlig.com: restock the usuals, plan dinners around the offers, find cheaper swaps, write the recipes. With a CLI and Python client.
SkillMITFew starsNo key
Tripmeter — a GNOME Shell extension for Claude Code and OpenAI Codex: usage limits and resets, plus what the same traffic would have cost at API rates, per model, per skill, per subagent and per MCP t
SkillMIT★ 1Few starsNo key
Agent Foundry is an open-source Codex Skill Pack for building production-ready AI-native products: SwiftUI iOS app using TCA / The Composable Architecture, Firebase backend, and backend-owned AI agent
SkillMIT★ 7No key
6-week intence course: build AI agents with OpenAI Agents SDK, CrewAI, LangGraph, AutoGen & MCP.
SkillMIT★ 2Few starsNo key
An AI coding-agent skill and CLI for right-sized software lifecycle documentation—from project context and traceable requirements to architecture, diagrams, decisions, quality, and operations.
SkillMIT★ 1Few starsNo key
Separates startup gaps that are real companies from features waiting to be cloned. Barred test (incumbent conflict) + Reach test (first 10-20 nameable users). Works across Claude Code, Cursor, Codex,
SkillMITFew starsNo key
Who stands behind it
