Loading…
/** @github-tools */
Best Agent Skills & Plugins on GitHub
Skill packs and plugins teach Claude Code, Codex and similar agents new habits and specialist knowledge. The useful ones change how the agent actually works, such as planning before coding or testing first, and come from a maintainer you can trust. Huge piles of prompts rarely help. Start with one workflow pack and the official libraries, then add a focused skill for the work you do most.
0 repos, each cloned and scanned
// top 10, ranked
Updated 30 October 2026 · moves since 26 October 2026 · re-ranked every 3 days on what readers use, never sponsored
- 1
Superpowers: A Disciplined Workflow for AI Coding Agents (GitHub, Scanned)
no changeMakes your coding agent brainstorm, plan, test first and review, the best first install for most users.
- 2
Anthropic Agent Skills: Ready-Made Skills for Claude (GitHub, Scanned)
no changeAnthropic's own skill library, including the document skills Claude uses, a trustworthy place to start.
- 3
Claude Plugins Official: Anthropic's Claude Code Plugin Directory (GitHub, Scanned)
no changeThe official Claude Code plugin marketplace, the easiest way to find and install vetted plugins.
- 4
Matt Pocock Skills: Engineering Workflows for Coding Agents (GitHub, Scanned)
no changeA small, focused set of skills for planning, testing and reviewing code, suited to careful developers.
- 5
Claude Code Templates: Agents, Commands, Hooks and MCPs in One Install (GitHub, Scanned)
no changeA catalog and CLI for adding ready agents, commands, hooks and MCP servers to Claude Code.
- 6
Vercel Skills CLI: Install Agent Skills in Any Coding Agent (GitHub, Scanned)
no changeThe npx skills command installs skills from GitHub into Claude Code, Codex, Cursor and more.
- 7
planning-with-files: Plans That Survive Your Agent's Memory Loss (GitHub, Scanned)
no changeKeeps your agent's plan in Markdown files so long tasks survive a cleared context.
- 8
Knowledge Work Plugins: Claude Skills for Every Role (GitHub, Scanned)
no changeAnthropic's plugins for sales, finance, legal and support, for people using Claude beyond coding.
- 9
UI UX Pro Max: Design Rules Your AI Agent Can Search (GitHub, Scanned)
no changeGives coding agents styles, palettes, font pairings and UX rules, helpful when building interfaces.
- 10
Trail of Bits Skills: Security Auditing Skills for Claude Code (GitHub, Scanned)
no changeA security firm's plugins for code audits, static analysis and fuzzing, for anyone shipping code that matters.
// all 22 in Agent Skills & Plugins
// nothing matches in this category yet
// How we scan
Before a repository gets a post here we clone it and run the same checks on every one. The scanner is a script in this site's own repository, its findings are written out with file and line, and a person reads every hit before writing the verdict in the post. The last full run was on Oct 28, 2026.
- Pinned commit
- A fresh clone of the default branch. The commit and date are on every report, so the findings are about one snapshot, not the repository in general.
- Secrets
- Credential patterns with a known shape: cloud access keys, API tokens for OpenAI, Anthropic, Slack, GitHub, Google and Stripe, chat webhooks, private key blocks.
- Suspicious code
- Code that decodes a string and then executes it, pipes a download straight into a shell, opens a raw socket to a shell, reaches a known exfiltration service, mines cryptocurrency, or looks packed.
- Install-time code
- npm lifecycle scripts, setup.py command classes, Cargo build scripts, and installer shell scripts: whether they use sudo, edit your shell profile, or fetch and run remote code.
- Committed binaries
- Executables and compiled objects identified by their bytes, not their file extension, so a renamed binary still shows up.
- CI workflows
- GitHub Actions that run on pull_request_target and check out the pull request head (a classic way to leak secrets), write-all permissions, and third-party actions pinned to a tag instead of a commit.
- Network hosts
- Every host the source code talks to, so an unexpected one stands out.
- Known vulnerabilities
- Every pinned dependency in the repository's lockfiles looked up in OSV.dev, counted by severity. Includes development dependencies, which is why the counts are not zero for a large web app.
- Project hygiene
- A security policy, automated dependency updates, CodeQL, a licence, contributing guidelines.
- OpenSSF Scorecard
- The Open Source Security Foundation's independent score, where the project has one.
Safe means no credential patterns, no decode-and-execute code, no exfiltration hosts, no undocumented install-time behaviour, no risky workflow, and nothing in the findings a reviewer could not explain. Anything you should know before installing (an installer that pipes to a shell, a tool that reads a credential you already have, a licence with conditions, or a lockfile with unpatched advisories) is the note beside the badge.
Not covered: we do not run the software, audit its logic, or review commits made after the scan. The date and commit are on every report. Check them, and read the code yourself before you trust it with anything that matters.
// Questions
- Are these GitHub AI tools free to use?
- All of them are free to download, run and modify. The licences differ: most are MIT or Apache 2.0, ComfyUI is GPL-3.0, and Open WebUI and Dify ship their own licences with conditions on rebranding and multi-tenant hosting. Each post says which licence applies and what it asks of you.
- What does it mean that a repository was scanned?
- We cloned it at a specific commit and ran the checks listed under How we scan: credential patterns, decode-and-execute code, install-time scripts, committed binaries, risky CI workflows, every host the code talks to, known vulnerabilities in pinned dependencies, and project hygiene. Every hit was read by a person before the verdict was written, and the findings are in each post.
- Why do known vulnerabilities show up in a scan marked safe?
- Because a lockfile pins development dependencies too. A large web app carries thousands of packages and OSV knows of advisories in some of them; most affect build tooling and never reach a user. Each post shows the counts per lockfile and the worst entries so you can see where they sit, and the notes say whether any of it ships to you.
- How current is a scan?
- The date and commit are printed in every post. Active projects merge dozens of commits a week, so treat a report as a snapshot of that commit, not a standing guarantee, and re-check the repository before installing anything on a machine you care about.
- Which of these should I start with?
- To run a model on your own computer, install Ollama and add Open WebUI for a chat interface. For images and video, ComfyUI. To build an app or agent without much code, Dify. To let an agent write code or use a browser, OpenHands, Codex or browser-use. If you already use Claude Code or Codex, cost-xray shows what each session actually costs.