★ 2 · Updated 2026-09-12
Runs periodic evaluation suites, analyzes test failures, updates lessons and instinct confidence, and tracks score history without human input.
Browse skills that share this tag.
★ 2 · Updated 2026-09-12
Runs periodic evaluation suites, analyzes test failures, updates lessons and instinct confidence, and tracks score history without human input.
★ 602 · Updated 2026-06-30
Synthesize feedback sources to generate prioritized curriculum revision recommendations with version tracking
★ 5 · Updated 2026-03-22
Transform raw plugin analysis results into actionable improvement recommendations for meta-skills ecosystem
★ 602 · Updated 2026-03-20
Evaluate and improve Claude skill quality through auditing
★ 5 · Updated 2026-03-10
Apply accumulated improvements from backlog to AI agent instructions
★ 18 · Updated 2026-02-23
Extract learnings from recent git commits and current conversation
★ 0 · Updated 2026-02-13
Framework for reviewing and improving agent skills against quality standards
★ 602 · Updated 2026-02-13
Improves skills based on evaluation results
★ 0 · Updated 2026-02-12
Iterates and improves Skills based on evaluation results
★ 18 · Updated 2026-02-12
Improves skills based on evaluation results when optimization is needed
★ 211 · Updated 2026-02-12
Iterates and improves other skills based on evaluation results