datallmhub

Gov Eval — Testing skill for Claude Code

Testing community

Run GovEval — the governance validation test suite.

How to install Gov Eval

Installs to ~/.claude/commands/datallmhub-claude-governance-gov-eval.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/datallmhub/claude-governance/HEAD/.claude/commands/gov-eval.md -o ~/.claude/commands/datallmhub-claude-governance-gov-eval.md

Restart Claude Code, or start a new session, for it to be picked up.

What Gov Eval does

Run GovEval — the governance validation test suite.

What this command does

Runs automated tests that verify the governance rules are actually followed. Each scenario sends a natural prompt to the generator, then an independent judge model scores the output.

Prerequisites

MISTRAL_API_KEY environment variable must be set (judge model)

Python 3.11+ with dependencies installed:

cd /tests && pip install -r requirements.txt

Steps

Read `.claude-governanc

Alternatives in Testing

Test Full — Run the full test suite across all tox environments with coverage enabled 1.1k ★
Check Package — Run full validation (build + lint + test + typecheck) on a package 1.1k ★
Test Marker — Create a simple test marker file for POC validation 229 ★