Humanity4AI ⭐

9 humanity skills for AI agents — crisis detection, accessibility auditing, empathy, cultural sensitivity, and more. Ready-to-use via MCP, npm, or direct prompting.

Skills at a Glance

⭐ If you find this useful, a star helps others discover it

Related MCP server: human-mcp

Quick Start

# One command — clone, install, verify, start
git clone https://github.com/humanity4ai/project_human.git && cd project_human && pnpm install && pnpm check && pnpm evals && pnpm start

Or use the npm package directly:

npx @humanity4ai/mcp-servers

Then add to your MCP client config:

{
  "mcpServers": {
    "humanity4ai": {
      "command": "pnpm",
      "args": ["--filter", "@humanity4ai/mcp-servers", "start"],
      "cwd": "/path/to/project_human"
    }
  }
}

All 9 skills are now discoverable via tools/list and invocable via tools/call.

Docker: docker compose up

Prerequisites: Node.js >= 22, pnpm >= 10 | Windows, macOS, Linux, Android, iOS

Three Ways to Use

See Agent Adapter Guide for platform-specific setup instructions.

Why Humanity4AI?

AI agents are everywhere — but they're not always humane. Humanity4AI gives agents reusable, tested skills for the moments that matter:

• An agent detects a user in crisis → Supportive Reply generates an appropriate response and escalates to qualified help

• A UI is inaccessible to screen readers → Accessibility Audit scores it against WCAG 2.2 and provides remediation

• Content uses stigmatising language → Safe Content Rewriter flags and rewrites harmful patterns

• A conflict is escalating → De-escalation Plan generates structured, non-coercive guidance

Every skill includes:

• Explicit safety boundaries — what the skill can and cannot do

• Uncertainty disclosure — confidence level stated upfront (low/medium/high)

• Evaluation gates — automated baseline checks for quality

These skills are rule-based and non-clinical — they do not provide diagnosis, treatment, or professional medical/legal advice.

Supported Platforms

OpenCode · Claude Code · Microsoft Copilot · Manus AI · OpenClaw · ChatGPT · Claude · Gemini

Contribute

git clone https://github.com/<your-username>/project_human.git
cd project_human
git checkout -b my-contribution
# Copy the skill template if adding a new skill:
cp -r templates/skill skills/my-skill-name
pnpm check && pnpm evals && pnpm test  # Run all checks before PR

Open a PR targeting main. Browse good first issues or read the Contributing Guide.

Resources

• Contributing Guide

• Agent Adapter Guide

• Governance

• Roadmap

• Release Process

• Public Site

Share on X · MIT License · Copyright © 2026 Ascent Partners Foundation