alirezarezvani/claude-skills

380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

Claude Code Skills & Plugins – a massive library of reusable AI‑agent capabilities

What it is – A single open‑source repository that bundles 364 “skills” (structured instruction packages) and 120 commands for 13 different AI‑coding agents (Claude Code, OpenAI Codex, Gemini CLI, Cursor, Aider, Hermes Agent, Mistral Vibe, etc.). Each skill lives in its own folder and contains:

  • SKILL.md – a markdown file that tells the agent what to do, how to reason, and which prompts or decision trees to follow.
  • Pure‑Python CLI helpers (667 scripts, std‑lib only) that the skill can call.
  • Reference assets such as templates, checklists, and domain‑specific knowledge files.

The repo also ships personas (pre‑configured agent identities) and an orchestration protocol that describes how to chain skills or hand‑off work between personas.

Why it matters

  • Tool‑agnostic – One source of truth; a conversion script (scripts/convert.sh) rewrites every skill into the native format required by each supported agent. You can install the same capability on Claude Code, Codex, Cursor, Aider, etc., with a single command.
  • Breadth of coverage – Skills span engineering (core & “POWERFUL” tier), product, marketing, research, regulatory compliance, C‑suite advisory, finance, operations, and more. The “POWERFUL” tier adds 25 production‑grade capabilities such as RAG pipeline builder, CI/CD generator, security auditor, and incident‑commander.
  • Zero‑dependency Python – All helper scripts run with the Python standard library, so they work on any machine that has Python installed.
  • Security‑first – A built‑in Skill Security Auditor scans a skill for command‑injection, prompt‑injection, and supply‑chain risks before installation.
  • Community‑validated – The repository shows a SkillCheck validation badge and has amassed 5 k+ GitHub stars, indicating strong community interest.

Quick start (Claude Code – the recommended host)

# Add the marketplace entry
/plugin marketplace add alirezarezvani/claude-skills

# Install a whole domain (e.g., engineering)
/plugin install engineering-skills@claude-code-skills

# Or install a single skill
/plugin install skill-security-auditor@claude-code-skills

For other agents the README provides one‑line wrappers, e.g. ./scripts/gemini-install.sh for Gemini CLI or python scripts/sync-hermes-skills.py for Hermes Agent.

Example workflows

Goal Persona(s) Skill chain (high‑level)
Architecture review startup-cto senior-architect → security-auditor → reliability‑portfolio
SEO‑optimized blog post growth-marketer content-creator → aeo (E‑E‑A‑T audit) → landing (optional HTML generator)
Regulatory compliance check c-level-advisor (CFO) + ra-qm-team mdr-745-specialist → compliance‑os → risk‑management
CI/CD pipeline generation devops‑engineer ci-cd-pipeline-builder → git‑worktree‑manager

The orchestration protocol (see orchestration/ORCHESTRATION.md) defines four patterns – Solo Sprint, Domain Deep‑Dive, Multi‑Agent Handoff, and Skill Chain – that let you mix and match personas and skills without writing extra code.

Strengths

  • Comprehensive catalog – 364 ready‑to‑use skills across 18 domains, plus 7 pre‑made personas.
  • Cross‑platform – Works with virtually every popular AI‑coding assistant today.
  • Low friction – All Python helpers are std‑lib only; installation is a single script per tool.
  • Security tooling – Built‑in auditor helps prevent malicious skill payloads.
  • Extensible – New skills can be added following the SKILL.md + scripts/ layout; personas can be cloned from a template.

Limitations / things to watch

  • Size and maintenance – With > 600 scripts, keeping every skill up‑to‑date with the latest language runtimes or cloud‑provider APIs may require community effort.
  • Agent‑specific nuances – Although conversion scripts handle format changes, some agents may not support every feature (e.g., complex loop orchestration) out of the box.
  • Learning curve for orchestration – The protocol is powerful but may be overkill for simple, single‑skill use cases.
  • No compiled binaries – All logic lives in Python scripts; performance‑critical tasks will still rely on the underlying LLM.

Who should use it

  • Developers who already use Claude Code, Codex, or similar agents and want to extend them with domain‑specific expertise without writing prompts from scratch.
  • Product & growth teams looking for AI‑assisted content creation, SEO, or market‑research pipelines.
  • Ops / security engineers who need automated audit, CI/CD, or incident‑response playbooks that can be invoked by an LLM.
  • Enterprises that want a unified library of compliance, finance, and C‑suite advisory skills that can be deployed across multiple AI agents.

Bottom line

alirezarezvani/claude-skills is a genuine, large‑scale open‑source effort to turn AI coding agents into multi‑disciplinary assistants. By packaging prompts, scripts, and reference data into reusable “skills” and providing a tool‑agnostic conversion pipeline, it lets teams quickly add production‑grade capabilities— from security audits to marketing copy— to any supported LLM‑powered coding assistant.

Related

  • Project
    Mathews-Tom/armory

    A curated library of production-grade agents, skills, and workflows for Claude Code and Claude.ai to enable professional, repeatable AI-driven software development.

  • Project
    shareAI-lab/learn-claude-code

    A 17‑lesson tutorial that teaches you how to build the surrounding “harness” code for an LLM‑based coding agent (Claude). It walks through adding tools, permissions, context management, memory, task scheduling, multi‑agent coordination, and goal‑driven termination, all around a simple agent‑loop that lets the model decide when to call tools.

  • Project
    sangrokjung/claude-forge

    A professional equipment pack for Claude Code that adds specialist agents, safety hooks, and automated workflows to transform the terminal AI into a full-scale development kit.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Project
    fcakyon/claude-codex-settings

    A collection of plug‑ins that extend Claude Code (and compatible tools) with code‑review, buzzword‑blocking, cross‑model advisors, concise output styles, smarter summarisation, telemetry and office‑document skills.