🧩 Skills in GitHub

Free web tool for visualizing and comparing the growth of GitHub repositories over time by star count. Also surfaces top GitHub repos.

A large open-source skill bundle giving Claude (via Claude Code / MCP-style skills) ready-made capabilities for scientific, data-science, and bio/chem/physics workflows.

An open-source library of 163 prewritten skills that turn any compatible AI coding/research agent into a more capable AI scientist for biology, chemistry, medicine, materials, physics, data science, and related fields.

A community-built, open-source library of hundreds of structured cybersecurity skills that give AI coding agents (Claude Code, Cursor, Copilot CLI, Gemini CLI, etc.) ready-made, framework-aligned security expertise.

An open-source context database for AI agents that unifies memory, knowledge (RAG), and skills into a single virtual filesystem (viking://) so agents can browse and retrieve context deterministically instead of treating vector stores as a black box.

A collection of production-grade, structured workflows ("skills") for AI coding agents that encode how senior engineers actually work across the software development lifecycle.

Prebuilt skills that let AI coding agents (Claude Code, Cursor, Hermes, OpenClaw, etc.) call a YouTube API to fetch transcripts, search videos, browse channels, and extract playlists — without Google's YouTube Data API, yt-dlp, or headless browsers.

An agent skill that rewrites AI-sounding text to read like a person wrote it, without changing the underlying facts or claims. Works with any agent that supports skills; implemented mostly as a Markdown spec (SKILL.md) plus a few helper files.

A local code-intelligence engine that builds a persistent knowledge graph of your codebase and exposes it via the Model Context Protocol (MCP), so agents like Claude Code, Cursor, and Codex can answer structural questions without reading every file.