All skills
evaluation-methodology
Explains how plugin quality is scored and how to improve a skill's triggering and orchestration.
- Part of wshobson/agents
- 7.8k installs
- AI Engineering · Evals and monitoring
More Evals and monitoring skills
See all- caveman-learn133kReviews a Caveman learn report, applies cost-lowering fixes with your consent and reports the savings.
- caveman-optimize132kTurns a Caveman optimization observation into a candidate with a baseline comparison, needing your approval.
- ai-prompt-engineering-safety-review10.5kReviews prompts for safety, bias, security and effectiveness, then suggests concrete improvements.
- agentic-eval10.3kSets up evaluation and self-critique loops to measure and improve AI agent output quality.
Also in this pack
- tailwind-design-system74.8kBuilds Tailwind CSS v4 design systems with tokens, component libraries and responsive patterns.
- nodejs-backend-patterns50.7kBuilds Node.js backends with Express or Fastify, covering middleware, auth, databases and API design.
- python-testing-patterns41.2kWrites Python tests with pytest, fixtures and mocking, following test-driven development practices.
- brand-landingpage40.1kInterviews you about your brand, then designs and iterates a polished landing page ready to deploy.