All skills
eval-dataset-design
Designs agent evaluation tasks and datasets, including validators, difficulty tiers, leak prevention and long-term upkeep.
- Part of bojieli/ai-agent-book
- AI Engineering · Evals and monitoring
More Evals and monitoring skills
See all- skillevaluator287Runs SkillEvaluator to score a SKILL.md, write test cases, explain reports and gate skills in CI.
- evaluating-llms-harness68Benchmarks language models on standard tests like MMLU and GSM8K.
- dspy26Writes and auto-optimizes DSPy programs for prompts and RAG pipelines.
- writing-instructions19Rewrites prompts and instructions so the model actually follows them.
Also in this pack
- ai-style16Checks Chinese copy against a checklist that removes the telltale tone of machine-written text.
- pptx14Generates a PowerPoint deck from a paper, outline or structured text.
- data_analysis4Runs auditable math and descriptive statistics on data you have already confirmed.
- coding3Writes and runs Python code to check that scripts and their output are correct.