evaluate-plugin

# Evaluate Plugin Quality Performs a multi-dimensional quality review of a Claude Code / Copilot plugin. Scores the plugin's skills, agents, commands, and hooks on how well their instructions will guide an LLM to produce correct, consistent, and useful behavior. ## When to use - User wants to evaluate a plugin before submitting a PR - User asks "how good is my plugin?" - User wants to improve their plugin's quality score - User asks to review or score a plugin ## Workflow ### Phase 1: Identify the plugin 1. If the user specifies a plugin name, locate it under `plugins/<name>/`. 2. If not specified, check the current working directory — if it's inside `plugins/`, use that plugin. 3. If ambiguous, ask the user which plugin to evaluate. ### Phase 2: Collect plugin content Gather ALL of the following files from the plugin directory (skip any that don't exist): - `.claude-plugin/plugin.json` — Plugin manifest - `agency.json` — Agency configuration - `README.md` — Plugin documentation - `skills/*/SKILL.md` — All skill definitions - `agents/*.md` — All agent definitions - `commands/*.md` — All command definitions - `hooks/hooks.json` — Hooks configuration - `scripts/*` — All implementation scripts (.ps1, .sh, .py, .js, etc.) - `tests/*` — All test files Read each file and assemble the content for review. ### Phase 3: Load evaluation criteria Load the criteria files from this skill's `criteria/` directory: - `criteria/_system.md` — Your evaluation persona and scoring sca...