toolkit-evolution

What problem does it solve?

Prevents the toolkit from stagnating or accumulating weak, unmeasured workflow gaps by running a structured, evidence-based self-improvement loop.

Core Features & Use Cases

• Closed-loop self-improvement pipeline: Runs scheduled or manual discovery, diagnosis, proposal, critique, build, A/B validate, and promotion with learning recorded.
• Evidence-gated decisions: Requires concrete routing failures, git churn signals, dream insights, and learning-db evidence; blocks speculative improvements.
• Branch-based implementation & A/B testing: Implements top winners on isolated feature branches, validates with deterministic checks, then compares outcomes against baseline before shipping.

Quick Start

Invoke toolkit self-improvement by running /evolve --discover to find missing skills and evidence-backed improvement opportunities.