All skills
agent-optimization
Improves an agent's state using versioned scores and linked traces from a fixed benchmark.
- Part of Prism-Shadow/penguin-harness
- 1 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.
- prompt-engineering-patterns24.8kDesigns, debugs and improves prompts using templates, chain-of-thought and few-shot patterns.
- llm-evaluation13.8kSets up automated metrics, human feedback and benchmarks to measure how well your LLM application performs.
Also in this pack
- humanizer2Rewrites or edits prose in any language so it reads like edited human writing rather than default AI output.
- ollama2Deploys and serves local models with Ollama and exposes an OpenAI-compatible endpoint to apps and agents.
- vllm2Deploys and serves language models with vLLM behind an OpenAI-compatible endpoint with tool calling.
- agent-evaluation1Runs one test agent on one benchmark case once, scores it privately and returns a single protocol result.