self-improving-agent-builder
Installation
SKILL.md
Self-Improving Agent Builder
Purpose
Run a closed-loop improvement cycle on any goal-seeking agent implementation:
EVAL -> ANALYZE -> RESEARCH -> IMPROVE -> RE-EVAL -> DECIDE -> (repeat)
Each iteration measures L1-L12 progressive test scores, identifies failures
with error_analyzer.py, runs a research step with hypothesis/evidence/
counter-arguments, applies targeted fixes, and gates promotion through
regression checks.