Skills Directory

Reusable coding rules & agent skills for Claude Code, Cursor, Copilot and more - copy, adapt, ship faster.

2 skills indexed across 13 categories

Results for “evaluation” - 2 found

llm-evaluation

565

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testi

Testingby wshobson/agents

Eval Before Switch

Blocks a production model change until a private eval has been run. Use before any model version bump or provider switch.

Testingby tokencalculator