by sjnims · Claude Skill · ★ 20
cc-plugin-eval A 4-stage evaluation framework for testing Claude Code plugin component triggering. Validates whether skills, agents, commands, hooks, and MCP servers correctly activate when expected. Why This Exists Claude Code plugins contain multiple component types (skills, agents, commands) that trigger based on user prompts. Testing these triggers manually is time-consuming and error-prone.
| Stars | 20 |
| Forks | 0 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 75.689512318572/100 |
| Open Issues | 10 |
| Last Updated | 2026-06-16 |
| Created | 2026-01-01 |
| Platforms | claude-code, cli, node |
| Est. Tokens | ~18k |
These tools work well together with cc-plugin-eval for enhanced workflows:
Explore other popular claude skill tools:
cc-plugin-eval is 4-stage evaluation framework for testing Claude Code plugin component triggering. Validates skills, agents, and commands activate correctly via programmatic detection and LLM judgment.. It is categorized as a Claude Skill with 20 GitHub stars.
cc-plugin-eval is primarily written in TypeScript. It covers topics such as ai-testing, anthropic, claude.
You can find installation instructions and usage details in the cc-plugin-eval GitHub repository at github.com/sjnims/cc-plugin-eval. The project has 20 stars and 0 forks, indicating an active community.
cc-plugin-eval is released under the MIT license, making it free to use and modify according to the license terms.