awesome-ai-agent-tools
Skill62 starsChanged 3 months agoCC0-1.0View on GitHub
Install and manage AI agent skills, MCP servers, and agent workflows from the Awesome AI Agent Tools collection. Use this when the user wants to install skills, set up MCP servers, browse agent workflows, or explore the AI agent tool ecosystem. Supports Claude Code, Cursor, Codex, OpenCode, Gemini CLI, Copilot, and 30+ agents.
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
When the user wants to install AI agent skills
- Distinctive: line 25
When the user wants to set up MCP servers
- Distinctive: line 26
When the user wants to browse or use agent workflows
- Distinctive: line 27
When the user asks about AI agent tools, skills, or MCPs
- Distinctive: line 28
When the user wants to explore the AI development ecosystem
- Very specific: line 151
All skills follow the SKILL.md open standard adopted by ~40 clients.
- Distinctive: line 204
Always verify a skill/MCP before recommending it
- Distinctive: line 205
Prefer official or well-maintained sources
- Very specific: line 207
Follow the SKILL.md standard for new skills
- Distinctive: line 212
When installing resources, confirm:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Awesome AI Agent Tools
Installable AI agent components for coding assistants: skills, MCP servers, agent workflows, subagents, hooks, plugins, prompts, and CLI tools.
What This Skill Does
This skill teaches you how to install and use resources from the Awesome AI Agent Tools collection. It covers three types of resources:
- Skills - Reusable SKILL.md instruction sets for specific tasks
- MCP Servers - Model Context Protocol servers for tool integration
- Agent Loops - Repeatable patterns with prompts and verification
When to Use
- When the user wants to install AI agent skills
- When the user wants to set up MCP servers
- When the user wants to browse or use agent workflows
- When the user asks about AI agent tools, skills, or MCPs
- When the user wants to explore the AI development ecosystem
Installation Methods
Method 1: Install via skills.sh CLI (Recommended)
The fastest way to install skills from this collection:
# Install all skills from this repo
npx skills add michielhdoteth/awesome-ai-agent-tools
# Install a specific skill
npx skills add michielhdoteth/awesome-ai-agent-tools --skill test-driven-development
# Search for skills by keyword
npx skills find "debugging"
# List installed skills
npx skills list
# Update all installed skills
npx skills updateMethod 2: Install via add-mcp CLI
For MCP servers, use the Neon add-mcp tool:
# Install a specific MCP server
npx add-mcp <url-or-package>
# Examples:
npx add-mcp https://mcp.neon.tech/mcp
npx add-mcp @upstash/context7-mcp
npx add-mcp @anthropic-ai/mcp-server-playwright
# Search for available servers
npx add-mcp find
# List supported agents
npx add-mcp list-agents
# Install for a specific agent
npx add-mcp -a cursor <url-or-package>
# Install globally
npx add-mcp -g <url-or-package>
# Skip prompts
npx add-mcp -y <url-or-package>Method 3: Clone and Copy
# Clone the full collection
git clone https://github.com/michielhdoteth/awesome-ai-agent-tools.git
cd awesome-ai-agent-tools
# Copy skills to your project
cp -r skills/test-driven-development/.claude/skills/ your-project/.claude/skills/
cp -r skills/test-driven-development/.opencode/skills/ your-project/.opencode/skills/
cp -r skills/test-driven-development/.agents/skills/ your-project/.agents/skills/Browsing Resources
Browse by category. Counts are deliberately omitted here because they change on
every merge; the authoritative counts are in each catalog.json.
Skills by Category
| Category | Top Skills |
| Development | test-driven-development, systematic-debugging, code-reviewer |
| Productivity | brainstorming, writing-plans, verification-before-completion |
| Design | figma-design-to-code, multimedia-generation, playwright-automation |
| Content | cold-email, copywriting, humanizer |
| Testing | webapp-testing, agent-browser |
| DevOps | devops-infrastructure, using-git-worktrees |
| Marketing | seo-audit, content-strategy |
| Data | data-analysis, supabase-postgres-best-practices |
| Security | mcp-security, security-guidance |
MCP Servers by Category
| Category | Top Servers |
| Official Reference | Filesystem, Fetch, Memory, Sequential Thinking, Git, Brave Search |
| Developer Tools | Context7, MarkItDown, GitHub MCP |
| Browser/Web | Playwright, Firecrawl |
| Databases | PostgreSQL, Neon, Supabase, MindsDB, Redis |
| Cloud Platforms | AWS, Cloudflare, DigitalOcean, Vercel |
| DevOps | Docker, Kubernetes, Terraform, Pulumi |
| Agent Orchestration | n8n, Ruflo, Claude-Flow |
Agent Loops by Category
| Category | Top Loops |
| Engineering | overnight-docs-sweep, alpha-loop, kitchenloop, autoloop |
| Evaluation | core-agentic-workflow, quality-streak-loop |
| Operations | agent-teams, dynamic-workflows, developer-os-memory |
| Content | content-refresh-loop, seo-geo-visibility-loop |
| Design | ui-ux-score-loop, accessibility-repair-loop |
Cross-Platform Compatibility
This collection works with every major AI coding assistant:
| Platform | Skills Path | MCP Support |
| Claude Code | .claude/skills/ | Yes |
| OpenCode | .opencode/skills/ | Yes |
| Codex | .agents/skills/ | Yes |
| Cursor | .cursor/skills/ | Yes |
| Gemini CLI | .gemini/skills/ | Yes |
| Copilot | .github/skills/ | Yes |
| Aider | .aider/skills/ | Yes |
| Windsurf | .windsurf/skills/ | Yes |
All skills follow the SKILL.md open standard adopted by ~40 clients.
Quick Install Commands
Popular Skills
# TDD workflow
npx skills add michielhdoteth/awesome-ai-agent-tools --skill test-driven-development
# Systematic debugging
npx skills add michielhdoteth/awesome-ai-agent-tools --skill systematic-debugging
# Code review
npx skills add michielhdoteth/awesome-ai-agent-tools --skill code-reviewer
# Brainstorming
npx skills add michielhdoteth/awesome-ai-agent-tools --skill brainstorming
# Writing plans
npx skills add michielhdoteth/awesome-ai-agent-tools --skill writing-plansPopular MCP Servers
# Context7 - Version-pinned library docs
npx add-mcp @upstash/context7-mcp
# Playwright - Browser automation
npx add-mcp @anthropic-ai/mcp-server-playwright
# Neon - Serverless Postgres
npx add-mcp https://mcp.neon.tech/mcp
# GitHub - Issues, PRs, code search
npx add-mcp @anthropic-ai/mcp-server-githubCatalog Files
For programmatic discovery, use the JSON catalogs:
skills/catalog.json- skills with metadatamcps/catalog.json- MCP servers with install commandsloops/catalog.json- agent workflows with prompts
Contributing
To add resources to this collection, see contributing.md.
Rules
- Always verify a skill/MCP before recommending it
- Prefer official or well-maintained sources
- Check cross-platform compatibility
- Follow the SKILL.md standard for new skills
- Attribute all sources properly
Output Format
When installing resources, confirm:
- What was installed (name, type)
- Where it was installed (path)
- How to use it (next steps)
- Any configuration needed
References
- GitHub Repository
- Skills.sh CLI - Official skill package manager
- add-mcp CLI - MCP server installer
- SKILL.md Standard - Open skill format
- MCP Documentation - Model Context Protocol
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

