All skills
metric-design
Designs and calibrates a trustworthy metric with guardrails before any optimization begins.
- Part of kirodotdev/KiroCrew
- 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
- gateway-restart2Restarts the Kiro Crew gateway from inside a session while keeping the conversation going.
- goal-loop2Starts a self-improving loop from a goal and folder, then runs it until the done criteria are met.
- grill2Questions you one branch at a time to align on a plan before committing to it.
- kirocrew-app-dev2Builds, packages and publishes Kiro Crew external apps, covering manifests, UI, crons and hooks.