sjnims/cc-plugin-eval
4-stage evaluation framework for testing Claude Code plugin component triggering. Validates skills, agents, and commands activate correctly via programmatic detection and LLM judgment.
This tool helps AI developers automatically test if their Claude Code plugin components trigger correctly based on user prompts. It takes your plugin's code as input and generates a comprehensive report indicating whether skills, agents, and commands activate as expected or unexpectedly. This is for AI developers, prompt engineers, and QA specialists who build and maintain Claude Code plugins.
Use this if you need to reliably verify that your Claude Code plugin's components (skills, agents, commands) activate precisely when intended by diverse user prompts.
Not ideal if you are testing general LLM conversational abilities or user interfaces outside of Claude Code plugin component triggering.
Stars
14
Forks
—
Language
TypeScript
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/sjnims/cc-plugin-eval"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hesreallyhim/awesome-claude-code
A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and...
bfly123/claude_code_bridge
Real-time multi-AI collaboration: Claude, Codex & Gemini with persistent context, minimal token overhead
fengshao1227/ccg-workflow
多模型协作开发系统 - Claude 编排 + Codex 后端 + Gemini 前端，28 个命令覆盖开发全流程，一键安装零配置
njbrake/agent-of-empires
Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI Coding Agent...
harikrishna8121999/antigravity-workflows
Community-driven workflows for Antigravity AI. Like Claude Skills - reusable prompts and...