Menu
Manage the gene pool — compounding library of proven skill improvement strategies. Use when user asks to view genes, check gene pool, apply a gene, or /gene.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when you need to generate or enhance user interface and user experience designs.
Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Clawdbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
Collaborative thinking partner for exploring complex problems through questioning
Use when you need to access and apply superpowers within your Claude projects.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
Use when you need to analyze your own reasoning process to improve accuracy.
| name | gene |
| description | Manage the gene pool — compounding library of proven skill improvement strategies. Use when user asks to view genes, check gene pool, apply a gene, or /gene. |
Implements EvoMap's Genome Evolution Protocol (GEP) locally: a content-addressable library of proven improvement strategies that grows more powerful with each skill evolution cycle.
Every successful skill-evolve improvement extracts a Gene — the pattern of what was broken
and how it was fixed. Future improvements try matching genes first (free, instant) before
falling back to AI generation. Confidence compounds: each re-application increases the gene's
trust score.
Gene types (EvoMap-inspired):
repair — fixes missing structure (Output section, code blocks, short descriptions)optimize — improves trigger clarity and invocation precisioninnovate — rewrites for clarity when no structural issue is detected# View all genes in the pool (sorted by confidence)
python3 _scripts/skill_evolution.py gene list
# Filter by type
python3 _scripts/skill_evolution.py gene list --type repair
# Gene pool statistics (most proven gene, average confidence)
python3 _scripts/skill_evolution.py gene stats
# Manually apply a specific gene to a skill
python3 _scripts/skill_evolution.py gene apply --id <gene_id> --skill <skill_name>
Genes are automatically extracted and applied during /skill skill-evolve evolve. You rarely
need to invoke this skill directly — the compounding happens in the background.
_logs/gene_pool.json — the growing library of proven strategies (content-addressable by SHA256)