| name | skill-evolve |
| description | Score skill fitness with GDI and auto-improve SKILL.md files using the gene pool (EvoMap) and compounding cycles (BotLearn). Use when user asks to improve skills, audit the skill ecosystem, run skill evolution, check skill health, or /skill-evolve. |
Skill Evolution (/skill-evolve)
Full EvoMap + BotLearn self-evolution loop for the PAI skill ecosystem:
EvoMap GDI scoring — every skill gets a fitness score:
GDI = usage_frequency(35%) + recency(30%) + content_quality(20%) + trigger_clarity(15%)
Gene pool (compounding) — proven improvement strategies accumulate in _logs/gene_pool.json.
Each successful improvement extracts a gene. Future improvements try matching genes first
(free, deterministic) before AI generation. Confidence grows with each application.
BotLearn loop — every evolution cycle makes the system smarter and cheaper to run.
Usage
python3 _scripts/skill_evolution.py fitness
python3 _scripts/skill_evolution.py fitness --priority high
python3 _scripts/skill_evolution.py evolve --skill <name>
python3 _scripts/skill_evolution.py evolve --all --priority high --confirm
python3 _scripts/skill_evolution.py gene list
python3 _scripts/skill_evolution.py gene stats
python3 _scripts/skill_evolution.py synthesize
python3 _scripts/skill_evolution.py report
Evolution Loop
skill_tracker_hook.py → _logs/skill_usage.json
↓
skill_evolution.py fitness (GDI scoring, no AI)
↓
skill_evolution.py evolve (gene pool first → AI fallback)
↓
extract gene → _logs/gene_pool.json (confidence compounds)
↓
next cycle: gene pool is smarter
Output
_logs/skill_usage.json — usage events (auto-populated by UserPromptSubmit hook)
_logs/gene_pool.json — compounding library of proven strategies
_logs/skill_backups/{skill}/{ts}/SKILL.md — pre-improvement snapshots
_logs/skill_evolution_applied.json — improvement history
Sources/Skill Fitness Report - YYYY-MM-DD.md — weekly report