AgentStack
MCP verified MIT Self-run

Agents And Skills

mcp-the-ai-directory-company-agents-and-skills · by The-AI-Directory-Company

70+ AI agent templates and 55+ skill definitions for Claude Code, Cursor, Windsurf, and other AI coding tools. Community-maintained, MIT licensed. Follows the Agent Skills specification.

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add mcp-the-ai-directory-company-agents-and-skills

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Agents And Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

AI Agent Templates & Skill Definitions

70+ AI agent templates and 55+ skill definitions for Claude Code, Cursor, Windsurf, and other AI coding tools. Community-maintained, MIT licensed.

[](https://github.com/The-AI-Directory-Company/agents-and-skills/actions/workflows/validate-pr.yml) [](LICENSE)

> Browse the full directory: AI Agent Templates | AI Skill Definitions


What Are AI Agent Templates?

AI agent templates are structured Markdown files that give AI coding assistants a specialized role. Each template defines a complete persona — expertise, decision-making frameworks, behavioral patterns, and communication style. When loaded into Claude Code, Cursor, or Windsurf, the AI assistant adopts that role and operates with domain-specific judgment.

Examples include:

  • Code Reviewer — catches bugs, security issues, and style violations with actionable feedback
  • Product Manager — writes PRDs, prioritizes features, and defines acceptance criteria
  • Data Scientist — analyzes datasets, builds models, and explains statistical results
  • Security Engineer — audits code for vulnerabilities and recommends mitigations
  • Technical Writer — creates documentation, API references, and developer guides

Browse all 70+ agents →

What Are AI Skill Definitions?

Skill definitions are composable, task-focused prompt templates for specific workflows. Unlike agents (which define who the AI becomes), skills define what the AI does — step-by-step instructions for a concrete task. Skills can include templates, checklists, scripts, and reference material.

Examples include:

Browse all 55+ skills →

How to Install

Claude Code Skills

Install any skill directly into your project:

npx skills add code-review-checklist

Or install manually — copy the skill folder into .claude/skills/ in your project:

cp -r skills/code-review-checklist .claude/skills/

Claude Code Agents

Copy the agent file into your project as a system prompt or CLAUDE.md context:

cp agents/code-reviewer.md .claude/agents/code-reviewer.md

Cursor & Windsurf

Agent and skill files are standard Markdown. Copy them into your project's AI configuration directory — .cursor/ for Cursor, .windsurf/ for Windsurf, or wherever your tool reads system prompts.

Specification

All content follows the Agent Skills specification — the open standard adopted by Claude Code, OpenAI Codex, Cursor, GitHub Copilot, Gemini CLI, and 25+ other AI tools.


Repository Structure

agents/
  CLAUDE.md              # Authoring guide for agent definitions
  *.md                   # One file per agent (filename = slug)
skills/
  CLAUDE.md              # Authoring guide for skill definitions
  /          # One folder per skill
    SKILL.md             # Required entrypoint (frontmatter + body)
    examples/            # Optional example outputs
    references/          # Optional reference material
    scripts/             # Optional automation scripts
    assets/              # Optional static files

Contributing

We welcome contributions from anyone. Whether you are adding a new agent, creating a skill, or improving an existing entry — your expertise makes this directory better for everyone.

Quick start:

  1. Fork this repo
  2. Read the authoring guide for your content type:
  • Agents: [agents/CLAUDE.md](agents/CLAUDE.md)
  • Skills: [skills/CLAUDE.md](skills/CLAUDE.md)
  1. Create your content following the spec
  2. Open a pull request — CI will validate your submission automatically

See [CONTRIBUTING.md](CONTRIBUTING.md) for the full guide, frontmatter spec, and quality bar.

Good First Contributions

New to open source or to this project? Look for issues labeled [good first issue](../../labels/good%20first%20issue) — they include clear instructions and pointers to similar existing entries.


How Validation Works

Every pull request is automatically checked by CI:

  • Frontmatter schema — Required fields present, correct types, valid categories
  • File structure — Filename/folder matches name field, skill folders contain SKILL.md
  • Cross-referencesworksWellWith* slugs point to entries that exist
  • Markdown lint — Basic formatting consistency

If a check fails, click the details link to see exactly what needs to be fixed. No local setup required.


Community

  • [Code of Conduct](CODEOFCONDUCT.md)
  • [Security Policy](SECURITY.md)
  • [Getting Help](SUPPORT.md)
  • Community Forum

License

[MIT](LICENSE) — The AI Directory Company

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.