skills
llms.txt1 starsChanged 41 days agoMITView on GitHub
An open-source (MIT) library of 354 production-ready agent skills, 82 installable plugins, 96 agents, and 102 slash commands across 18 domains — engineering, product, marketing, compliance, finance, research, and more. Each skill is a self-contained package bundling domain expertise, deterministic Python tools (stdlib-only, no LLM calls), reference knowledge bases, and ready-to-use templates. Skills are portable across Claude Code, OpenAI Codex, Gemini CLI, Cursor, Hermes Agent, Mistral Vibe, OpenClaw, and 6+ more AI coding tools. This file follows the llms.txt convention.…
Files
# Claude Code Skills & Agent Plugins > An open-source (MIT) library of 354 production-ready agent skills, 82 installable plugins, 96 agents, and 102 slash commands across 18 domains — engineering, product, marketing, compliance, finance, research, and more. Each skill is a self-contained package bundling domain expertise, deterministic Python tools (stdlib-only, no LLM calls), reference knowledge bases, and ready-to-use templates. Skills are portable across Claude Code, OpenAI Codex, Gemini CLI, Cursor, Hermes Agent, Mistral Vibe, OpenClaw, and 6+ more AI coding tools. This file follows the [llms.txt](https://llmstxt.org) convention. For a full, self-contained description of the entire repository, see [llms-full.txt](https://alirezarezvani.github.io/claude-skills/llms-full.txt). Key facts for agents: - **License:** MIT. Free to extract, deploy, and adapt. - **Repository:** https://github.com/alirezarezvani/claude-skills - **Distribution:** Claude Code plugin marketplace + ClawHub registry. - **Design philosophy:** Algorithm over AI (deterministic code, not LLM calls in tools), documentation-driven, template-heavy, self-contained skills. - **Skill package shape:** `SKILL.md` (master doc) + `scripts/` (Python CLI tools) + `references/` (knowledge bases) + `assets/` (templates). ## Getting started - [Home](https://alirezarezvani.github.io/claude-skills/): Overview and value proposition. - [Getting Started](https://alirezarezvani.github.io/claude-skills/getting-started/): Install and use skills/plugins. - [Multi-Tool Integrations](https://alirezarezvani.github.io/claude-skills/integrations/): Using skills with Codex, Gemini CLI, Cursor, Hermes, Vibe, OpenClaw, and more. - [Skills Overview](https://alirezarezvani.github.io/claude-skills/skills/): Index of all 354 skills by domain. - [Plugins](https://alirezarezvani.github.io/claude-skills/plugins/): The 82 installable marketplace plugins. - [Agents](https://alirezarezvani.github.io/claude-skills/agents/): The 96 cs-* agents and personas. - [Commands](https://alirezarezvani.github.io/claude-skills/commands/): The 102 slash commands. ## Domains - [Engineering — Core](https://alirezarezvani.github.io/claude-skills/skills/engineering-team/): Fullstack, AI/ML, DevOps, security, data, QA. - [Engineering — POWERFUL](https://alirezarezvani.github.io/claude-skills/skills/engineering/): Agent design, RAG, MCP, CI/CD, observability, SLOs, skill authoring. - [Product](https://alirezarezvani.github.io/claude-skills/skills/product-team/): RICE, OKRs, user stories, UX research, SaaS scaffolding. - [Marketing](https://alirezarezvani.github.io/claude-skills/skills/marketing-skill/): Content, SEO, AEO, ASO, demand gen, campaign analytics. - [Project Management](https://alirezarezvani.github.io/claude-skills/skills/project-management/): Jira/Confluence, Atlassian MCP, scrum. - [C-Level Advisory](https://alirezarezvani.github.io/claude-skills/skills/c-level-advisor/): Full C-suite advisors + founder-mode orchestration. - [Regulatory & Quality](https://alirezarezvani.github.io/claude-skills/skills/ra-qm-team/): ISO 13485, MDR, FDA, GDPR, ISO 27001. - [Compliance OS](https://alirezarezvani.github.io/claude-skills/skills/compliance-os/): Audit-prep orchestrator for SOC 2, ISO, GDPR, EU AI Act. - [Business & Growth](https://alirezarezvani.github.io/claude-skills/skills/business-growth/): Customer success, sales engineering, revenue operations. - [Business Operations](https://alirezarezvani.github.io/claude-skills/skills/business-operations/): Process mapping, vendor management, capacity planning. - [Commercial](https://alirezarezvani.github.io/claude-skills/skills/commercial/): Pricing, deal desk, partnerships, RFP response. - [Finance](https://alirezarezvani.github.io/claude-skills/skills/finance/): Financial analysis, DCF valuation, SaaS metrics. - [Research](https://alirezarezvani.github.io/claude-skills/skills/research/): Literature review, grants, patents, entity dossiers. - [Research Operations](https://alirezarezvani.github.io/claude-skills/skills/research-ops/): Clinical study design, R&D finance, market/product research. - [Productivity](https://alirezarezvani.github.io/claude-skills/skills/productivity/): Capture, email triage, reflection, handoff. - [Markdown to HTML](https://alirezarezvani.github.io/claude-skills/skills/markdown-html/): Markdown-to-interactive-HTML converter suite. ## Optional - [Guides](https://alirezarezvani.github.io/claude-skills/guides/best-claude-code-plugins/): Best plugins, per-tool skill guides (Codex, Gemini CLI, Cursor, OpenClaw). - [Orchestration](https://alirezarezvani.github.io/claude-skills/orchestration/): How skills chain together. - [Custom GPTs](https://alirezarezvani.github.io/claude-skills/custom-gpts/): Using the library with custom GPTs. - [Personas](https://alirezarezvani.github.io/claude-skills/personas/): Startup CTO, Growth Marketer, Solo Founder bundles.
Trending
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Other versions5 projects use a version of this.
Word for word · 5
- alirezarezvani/claude-skills★ 29k100% same
- GongYuanCaiJi/dsh-claude-skills★ 1100% same
- skaahgroup-a11y/skills★ 1100% same
- gladkovtimoxa-alt/claude-skills★ 0100% same
- SirkoBot007/claude-skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository57 other files it gives its agents.
- agent-launcher/CLAUDE.mdCLAUDE.md
- agents/CLAUDE.mdCLAUDE.md
- business-growth/CLAUDE.mdCLAUDE.md
- business-operations/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- c-level-advisor/CLAUDE.mdCLAUDE.md
- commercial/CLAUDE.mdCLAUDE.md
- engineering-team/CLAUDE.mdCLAUDE.md
- finance/CLAUDE.mdCLAUDE.md
- markdown-html/CLAUDE.mdCLAUDE.md
- marketing-skill/CLAUDE.mdCLAUDE.md
- product-team/CLAUDE.mdCLAUDE.md
- project-management/CLAUDE.mdCLAUDE.md
- ra-qm-team/CLAUDE.mdCLAUDE.md
- research-ops/CLAUDE.mdCLAUDE.md
- standards/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- docs/llms-full.txtllms.txt
- agent-memorySkill
- agent-securitySkill
- answer-verifierSkill
- api-securitySkill
- authorized-security-assessmentSkill
- container-securitySkill
- contract-first-clean-archSkill
- coordinate-implementationSkill
- dast-configSkill
- dependency-scanningSkill
- doubt-driven-developmentSkill
- evidence-gateSkill
- firewall-reviewSkill
- human-inputSkill
- hyperagent-eval-skillSkill
- iac-securitySkill
- intent-lockSkill
- interview-meSkill
- mcp-auditorSkill
- memory-graphSkill
- segmentationSkill
- owasp-top-10-webSkill
- prompt-injectionSkill
- prompt-injection-detectorSkill
- pr-reviewSkill
- repo-kickstartSkill
- restricted-defensive-validationSkill
- sast-configSkill
- secrets-managementSkill
- secure-code-reviewSkill
- security-and-hardeningSkill
- setup-project-memorySkill
- skill-auditorSkill
- solo-founderSkill
- source-driven-developmentSkill
- take-ownershipSkill
- threat-modelingSkill
- wrap-upSkill
- loop-librarySkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.