All skills
improve-judge
Refines the shared judge model using rollout evidence, human labels, and safe calibration.
- Part of experientiallabs/experiential
- 2 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
- ready-for-merge2Runs a pre-merge review, fixes comments, and checks the diff against project rules.
- test-build2Runs the Experiential build-to-serve path end to end as an unattended automation.
- test-gateway2Tests the Experiential local gateway end to end, including setup, routes, and usage tracking.
- video-create2Plans and renders professional videos from code, with optional voiceover and AI footage.