SkillDiff
Community library

Discover and share AI agent skills.

Community-maintained workflows for OpenAI Codex and Anthropic Claude—so you spend less time prompting and more time shipping.

  • Discover community skills
  • Install via GitHub PR
  • Read the full SKILL.md
  • Works with Codex + Claude

Find a skill

Search the community library and install to your repo.

Quick filters:

How SkillDiff works

A simple loop: discover → install → stay current.

🔎 Discover

Browse skills made for Codex and Claude.

🧩 Install

Open the SKILL.md and add it to your repo via GitHub PR.

🔔 Stay current

Follow topics and keep your assistant up to date.

Trending skills

View all

threat-hunting

Proactively search for security threats, vulnerabilities, and suspicious patterns in applications and infrastructure before they cause damage. Use when conducting security audits, identifying vulnerabilities, analyzing security logs, detecting suspicious patterns, investigating potential breaches, performing penetration testing, or implementing security monitoring.

test-fixing

Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.

hugging-face-evaluation

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

vercel-deploy

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

Contribute a skill

Share a repeatable workflow and help others ship faster.