SkillAgentSearch skills...

collection

A Free, Open Source, collection of personas, prompts, skills, memories, agents, and more. Use them directly through the DollhouseMCP Server

Install / Use

claude mcp add DollhouseMCP -- npx -y github:DollhouseMCP/collection

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

83/100

Supported Platforms

Claude Code
Claude Desktop
Cursor
Windsurf
OpenAI Codex

Tags

Our assessment of collection

collection scores 83/100 on our quality scale, 1498th of 3,055 Development & Engineering skills we index (top 50%).

Its MCP Server is 9.5 KB long, well organised into 38 sections with 5 code examples: a thorough specification that gives an agent plenty to work with.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
29/30
Structure
20/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so collection is actively maintained.
  • Our last check on 2026-09-25 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 85/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

collection compared with similar skills

All 4 of these similar skills score higher than collection; compare them before choosing.

SkillScoreStarsUpdatedFormat
collection (this skill)by DollhouseMCP831055d agoMCP Server
Agent-Reachby Panniantong10085.9k12d agoCLAUDE.md
headroomby headroomlabs-ai10074.0k1d agoCLAUDE.md
rufloby ruvnet10073.4ktodayCLAUDE.md
CowAgentby zhayujie10047.1ktodayCLAUDE.md

Frequently asked questions

How do I install collection?
Run claude mcp add DollhouseMCP -- npx -y github:DollhouseMCP/collection. The install tabs above show the steps for each supported agent.
Which AI agents does collection work with?
It is written for Claude Code, Claude Desktop, Cursor, Windsurf and OpenAI Codex, as a MCP Server file. Other agents that read the same format can often use it too.
Is collection safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 85/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is collection still maintained?
The repository was last updated about 2 months ago, so collection is actively maintained.

DollhouseMCP Collection

<div align="center">

📚 The Official Content Collection for DollhouseMCP 📚

Status & Quality

GitHub Views Version GitHub Pages Build Status Security Scan Validation

Compatibility & Technology

MCP Compatible Claude Desktop Node.js TypeScript

Collection Stats

Elements Active Categories Coming Soon Contributors

Documentation & Resources

Documentation API Reference Quick Start Examples Roadmap

Legal & Community

License: AGPL v3 Content License PRs Welcome

</div>

🌟 What is the DollhouseMCP Collection?

The DollhouseMCP Collection is a comprehensive library of AI-enhancing content including personas, skills, agents, prompts, templates, tools, and ensembles. Built for the Model Context Protocol (MCP), it provides a secure, curated ecosystem for AI augmentation.

📦 Content Types

✅ Active Categories

  • 🎭 Personas (6 available) - AI behavioral profiles and character definitions
  • 📄 Templates (10 available) - Document and workflow templates
  • 🤖 Agents (6 available) - Autonomous AI agents for specific tasks
  • 🛠️ Skills (11 available) - Functional capabilities and specialized abilities

🚧 Coming Soon

  • 💬 Prompts (1 in development) - Optimized prompt templates and chains
  • 🧠 Memories (3 in development) - Persistent context and knowledge storage
  • 👥 Ensembles (6 in development) - Curated collections for complex workflows
  • 🔧 Tools (1 in development) - MCP-compatible tools and utilities

📈 Live Statistics

<div align="center">

Collection Growth

<!-- These will be dynamically updated -->

Total Elements: 44 | Last Updated: 2025-08-28

Recent Additions

  • 🆕 Full-Stack Developer Ensemble
  • 🆕 React Expert Agent
  • 🆕 API Documentation Template
  • 🆕 Code Review Skill
  • 🆕 Creative Writer Persona

View Full Catalog →

</div>

🚀 Quick Start

Browse Content

Content is organized in three main areas:

  1. ✨ Showcase - Featured and recommended content
  2. 📚 Library - Free community-contributed content
  3. 💎 Catalog - Premium content (coming soon)

Using with DollhouseMCP

When using the DollhouseMCP server with Claude or another AI assistant:

# Browse all content
browse_collection

# Browse specific category
browse_collection "personas"

# Search for content
search_collection "creative writing"

# Get details
get_collection_item "persona" "creative-writer-pro"

# Create and submit new content (coming soon!)
create_persona "My Expert Helper" "A specialized assistant for..."
validate_content "My Expert Helper"
submit_to_collection "My Expert Helper"

The MCP server handles all the complexity - just describe what you want to create!

🏗️ Repository Structure

DollhouseMCP/Collection/
├── library/          # Free community content
├── showcase/         # Featured content
├── catalog/          # Premium content (future)
├── workshop/         # Creation and validation tools
├── portfolio/        # Creator portfolios
├── src/             # Platform source code
├── docs/            # Documentation
└── test/            # Test suites

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details on:

  • Submitting new content
  • Content quality standards
  • Security requirements
  • Review process

Submission Methods

1. Direct MCP Server Submission (Recommended)

Soon, you'll be able to contribute directly while chatting with Claude or any AI using the DollhouseMCP server:

create_content "My Amazing Persona" "persona" "A helpful assistant that..." 
submit_to_collection "My Amazing Persona"

The AI will guide you through the process, validate your content, and submit it for review - all within your chat session!

2. Build Your Own Tools

Our validation system is open source! You can create your own tools to:

  • Bulk import existing personas, prompts, or tools
  • Generate content programmatically
  • Integrate with your workflow
  • Submit PRs automatically

The validation API ensures all content meets quality and security standards:

import { ContentValidator } from '@dollhousemcp/collection';
const validator = new ContentValidator();
const result = await validator.validateContent('my-content.md');

3. Traditional GitHub Flow

  1. Fork the repository
  2. Create your content following our templates
  3. Run validation: npm run validate
  4. Submit a pull request

🔒 Security

All content undergoes strict security validation to ensure safety. See our Security Policy for details.

📜 Licensing

This project uses a dual licensing model:

  • Platform Code: AGPL-3.0 - Free for non-commercial use
  • User Content: Custom License - Creator retains ownership

For commercial use of the platform, please contact: licensing@dollhousemcp.com

🗺️ Architecture

<details> <summary>Click to view the element submission flow</summary>
graph TD
    A[User Creates Element] -->|Using MCP Server| B[Local Portfolio]
    B -->|Validate & Test| C[Personal GitHub Portfolio]
    C -->|Submit Issue| D[DollhouseMCP Collection]
    D -->|Review Process| E{Quality Check}
    E -->|Pass| F[Merge to Collection]
    E -->|Fail| G[Request Changes]
    F -->|Available| H[Community Downloads]
    H -->|Install| B
</details>

🌐 Links

📅 Changelog

[v1.0.3] - 2025-08-28

  • 📚 Added comprehensive documentation (ROADMAP, VALIDATION, SECURITY, QUICK_START)
  • 🎯 Enhanced README with professional badges and organization
  • 📝 Created examples directory with implementation guides
  • ✨ Improved collection statistics and live data sections

[v1.0.2] - 2025-08-28

  • 🚀 Added GitHub Pages deployment
  • 📄 HTML catalog generation
  • 🔒 XSS protection and content security
  • 📦 JSON API endpoint at /collection-index.json

[v1.0.1] - 2025-08-27

  • ✨ Initial collection structure
  • 🛡️ Security validation system
  • 📚 44 founding elements

Full Changelog →

🏆 Security & Trust

<div align="center">

Security Features

  • 🛡️ 100% Content Validation - Every element scanned for security issues
  • 🔍 Pattern Detection - AI injection & malicious prompt prevention
  • ✅ Automated Testing - 197+ security tests on every submission
  • 📊 Audit Logging - Complete security event tracking

Security Documentation →

</div>
<div align="center">

Contributing

We welcome contributions! Check out our Contributing Guide to get started.

For PR submission walkthrough, visit our Contribution Tutorial

</div>
<div align="center"> Made with ❤️ by the DollhouseMCP Team

Report Issue | Request Feature | Join Discussion

</div>

Related Skills

View on GitHub
GitHub Stars10
CategoryDevelopment
Updated1mo ago
Forks3

Languages

TypeScript

Trust signals

85/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 info