Guidelines

About Agent Skills

Agent Skills are a simple, open format for giving AI agents new capabilities and expertise.

Skills are structured folders of instructions, scripts, and resources that agents can discover and use to perform better at specific tasks.

Write once. Use everywhere.

The format is designed to be portable, composable, and interoperable across agent systems.

Getting Started

Agent Skills is an open format maintained by Anthropic and open to community contributions.

Code is licensed under Apache 2.0. Documentation is licensed under CC-BY-4.0.

SkillsMD builds on this open foundation while introducing identity, credibility, and professional attribution.


SkillsMD Standards

SkillsMD exists to document real, field-tested expertise. Every skill published here should reflect lived experience, not theoretical knowledge.

This page outlines the standards we expect from contributors.


1. Authorship & Identity

  • All skills must be submitted through LinkedIn authentication.
  • The submitting individual must have demonstrable experience in the domain.
  • If publishing under a company page, the individual contributor must still be identified.
  • Anonymous submissions are not permitted.

Skills are tied to people. Reputation matters.


2. What Qualifies as a Skill

A skill on SkillsMD is:

  • Specific, not generic
  • Operational, not motivational
  • Transferable, not autobiographical
  • Actionable in real business contexts

A skill is not:

  • A thought piece
  • A vague best-practice list
  • A rewritten blog article
  • AI-generated filler without applied insight

If it cannot be executed, it does not qualify.


3. Evidence & Credibility

Where applicable, skills should reference:

  • Context (industry, stage, company size)
  • Measurable outcomes
  • Constraints or trade-offs
  • Tools, frameworks, or systems used

Clarity builds trust. Specificity builds authority.


4. Originality

Submissions must:

  • Be written in your own words
  • Reflect your direct experience
  • Avoid copying proprietary frameworks without permission

AI assistance is allowed. Fabrication is not.


5. Quality Standards

We value:

  • Structured thinking
  • Concise language
  • Clear formatting
  • Professional tone

Avoid:

  • Excessive jargon
  • Marketing claims
  • Self-promotion
  • Affiliate links

This is a directory of expertise, not a distribution channel.


6. Moderation

All submissions may be:

  • Reviewed before publication
  • Edited for clarity
  • Rejected if they do not meet standards

Repeated low-quality submissions may result in removal of publishing privileges.


7. Ownership & Editing

You retain authorship of your skills. You may update or refine them over time.

Skills evolve. So should documentation.


8. Community Conduct

Respect the craft. Respect other contributors. Disagreements are welcome. Dismissiveness is not.

This is a professional archive, not a comment feed.


Important Links & Additional Reading

Official documentation and ecosystem references:

Claude Code Skills Documentation

https://code.claude.com/docs/en/skills

Agent Skills GitHub Repository

https://github.com/agentskills/agentskills

Agent Skills Official Site

https://agentskills.io/home

Claude Platform – Agent Skills Overview

https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview

The Complete Guide to Building Skills for Claude (PDF)

https://resources.anthropic.com/hubfs/The-Complete-Guide-to-Building-Skill-for-Claude.pdf

OpenAI Codex Skills Documentation

https://developers.openai.com/codex/skills/

OpenAI Skills GitHub Repository

https://github.com/openai/skills