Marketplace for trusted AI agent skills

Test Claude Code plugin and skill triggering with staged eval runs using cc-plugin-eval

Skill Detail

Test Claude Code plugin and skill triggering with staged eval runs using cc-plugin-eval

Run staged evaluations against a Claude Code plugin to verify that skills, agents, commands, hooks, and MCP components trigger when they should.

Code Quality & ReviewClaude Code
Code Quality & Review Claude Code Security Reviewed
⭐ 16 GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill test-claude-code-plugin-and-skill-triggering-with-staged-eval-runs-using-cc-plugin-eval Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
View source
At a glance
Tools required
Node.js 20+, Anthropic API key, Claude Code plugin directory
Install & setup
Clone the repo, run `npm install` and `npm run build`, set `ANTHROPIC_API_KEY` in `.env`, then run `npx cc-plugin-eval run -p ./path/to/your/plugin` or start with `–dry-run` for an estimate.
Author
sjnims
Publisher
Individual
Last updated
Apr 18, 2026
Quick brief

Use cc-plugin-eval when you need to validate whether a Claude Code plugin component actually triggers under positive, negative, paraphrased, and semantic prompt variants before release. Invoke it instead of relying on manual spot checks when the job is structured trigger analysis, scenario generation, execution, and metric reporting for Claude Code plugins, not generic LLM evals. The scope boundary is tight: this is a plugin-trigger evaluation workflow for Claude Code components rather than a general framework or SDK listing.