evaluate-plugin
Installation
SKILL.md
Evaluate Plugin
Use this skill when the target is a plugin root with .codex-plugin/plugin.json.
Workflow
- Treat "Evaluate this plugin." as the default entrypoint.
- If the request comes in as natural chat language, use
plugin-eval start <plugin-root> --request "<user request>" --format markdownfirst so the user sees the routed local path. - Run
plugin-eval analyze <plugin-root> --format markdown. - Read
Fix Firstbefore drilling into manifest findings, nested skill findings, and code or coverage details. - If the plugin contains multiple skills, summarize the strongest and weakest ones explicitly.
- If the user wants measured usage, switch to "Help me benchmark this plugin." and use the starter benchmark flow.
- If the user wants trend data, compare two JSON outputs with
plugin-eval compare.