legal-evaluator

90 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By fedec65/bettercallclaude (GitHub) · coding · 47 stars · scanned at commit 29f2587

Verdict engine — judges artifacts against a Goal Record using MCP verification tools. Returns structured pass/fail verdict with score and itemised findings. Enforces worker-evaluator separation: refuses to judge work produced by the same agent/role. Used by /legal-loop. Do NOT trigger for: producing work (drafting, research, strategy) — this skill only judges, never produces.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this. It runs automatically when the plugin is installed. Expected for a coding skill.

Found in 2 places.

bettercallclaude/.mcp.json, line 40"command": "node",
bettercallclaude/hooks/hooks.json, line 10"command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/privacy-check.js\"",

Connects to the internet

The author does not mention this. It runs automatically when the plugin is installed.

Found in 2 places.

bettercallclaude/hooks/hooks.json, line 2"description": "Anwaltsgeheimnis (attorney-client privilege) detection for Swiss law practice. Scans Write/Edit/MultiEdit/Bash/WebFetch and all MCP tool inputs
bettercallclaude/hooks/hooks.json, line 6"matcher": "Write|Edit|MultiEdit|Bash|WebFetch|mcp__.*",

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'legal-evaluator' ] || [ -L ~/.agents/skills/'legal-evaluator' ]; then echo 'A skill folder named legal-evaluator already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/fedec65/bettercallclaude' "$d" && git -C "$d" checkout --quiet '29f2587916d3ddae4e6ce861703a907fc61a9727' -- 'bettercallclaude/skills/legal-evaluator' && mkdir -p ~/.agents/skills && cp -R "$d"/'bettercallclaude/skills/legal-evaluator' ~/.agents/skills/'legal-evaluator' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'legal-evaluator' ~/.claude/skills/'legal-evaluator' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for fedec65/bettercallclaude shows the score of its lowest-scoring skill.

SkillTrust badge for fedec65/bettercallclaude

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/fedec65/bettercallclaude.svg)](https://zalavijaysinh.github.io/skilltrust/repos/fedec65/bettercallclaude/)

Score history

Date	Version	Score
2026-11-07	`29f2587`	90