ellehelvig

Hr AI Transformation Playbook — AI skill for Claude Code

AI community

HR AI transformation toolkit: vetted use cases, governance verified weekly against primary sources, a tested MCP server, installable agent skills, executable notebooks, and launch-blocking evals.

How to install Hr AI Transformation Playbook

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ellehelvig/hr-ai-transformation-playbook and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Hr AI Transformation Playbook does

HR AI transformation toolkit: vetted use cases, governance verified weekly against primary sources, a tested MCP server, installable agent skills, executable notebooks, and launch-blocking evals. MIT.

Alternatives in AI

Claude Cookbook — Official notebooks and recipes for common patterns (RAG, tool use, Skills, MCP) 35.3k ★
AGENTS.md - Skill Seekers — Concise reference for AI coding agents 11.1k ★
Visual Skills — AI film director skills for agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for 212 ★

README

HR AI Transformation Playbook

A working toolkit for HR and People teams putting AI into production responsibly: use cases, prompts, governance that survives legal review, executable notebooks, a tested MCP server, and installable agent skills.

[![CI](https://github.com/ellehelvig/hr-ai-transformation-playbook/actions/workflows/ci.yml/badge.svg)](https://github.com/ellehelvig/hr-ai-transformation-playbook/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-lightgrey.svg)](LICENSE) [![Regulatory content verified weekly](https://img.shields.io/badge/regulatory%20content-verified%20weekly-blue.svg)](CHANGELOG.md) [![Contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg)](CONTRIBUTING.md)

What makes this different

Most HR AI guidance is either too abstract to act on or too tied to one vendor to reuse. This repo is neither, and you can check that claim against the repo itself:

It runs. Three notebooks execute in CI on every push. Four MCP tools ship with a 32-test suite. The 29-case eval runner exits non-zero when a refusal or escalation gate fails, so it can block a deploy, and its scorer has tests of its own.
Governance is verified, not vibes. Every regulatory claim cites a primary source and is re-checked weekly against the statute, regulator page, or court docket. When something changes (the EU AI Omnibus, Colorado's rewrite, Illinois penalties), the docs change within days and the changelog says what moved.
Humans stay in the loop by construction. The MCP tools have human_review_required: true with no code path that turns it off, and the resume screener's schema is tested to guarantee it can never emit a score.
It's vendor-agnostic. Nothing assumes a specific HRIS, ATS, or model provider.