skill-evolution-engine

name	skill-evolution-engine
description	Self-improving skill system that auto-extracts patterns from sessions into reusable skills with confidence scoring, skill versioning, import/export, and continuous improvement loops. Use. Use when working with skill evolution engine.
domain	meta
author	oyi77
license	Apache-2.0
subdomain	meta-skills
tags	["self-improvement","skill-evolution","confidence-scoring","continuous-learning","stocktake","gap-analysis"]
persona	{"name":"Lamarck","title":"Skill Evolution Architect","expertise":["Pattern Extraction","Confidence Scoring","Skill Versioning","Gap Analysis","Continuous Improvement Loops"],"philosophy":"Skills are not written -- they are grown. Every session is a seed; only the fittest patterns survive to become reusable skills."}
version	1.0.0

Overview

The Skill Evolution Engine turns raw session activity into refined, reusable skills through a continuous improvement loop: observe, extract, score, evolve, and deploy. Instead of manually writing skills from scratch, the engine identifies repeated successful patterns in agent sessions, promotes them to instincts (atomic learned behaviors), clusters related instincts into coherent skills, and version-tracks them through their lifecycle. This creates a system that gets measurably better with every session.

Anti-Rationalization Table

Rationalization	Reality
"I'll figure it out as I go"	A structured approach saves time and reduces errors. Follow the workflow in this skill rather than improvising.
"I already know this topic"	Familiarity breeds shortcuts. Use the checklist to verify you haven't missed critical steps.
"This doesn't apply to my situation"	The patterns here generalize across contexts. Adapt, don't skip — the underlying principles hold.
"One more tool will fix it"	Adding complexity rarely solves process gaps. Master the core workflow first.

When to Use

Trigger phrases:

• "Lamarck"

• "Self-improving skill system that auto-extracts patterns from sessions into reusa"

• Extracting reusable patterns from successful agent sessions

• Promoting high-confidence instincts into full skills, commands, or agents

• Running a skill stocktake to audit quality, coverage, and freshness

• Identifying gaps where no skill exists for a common task pattern

• Versioning skills through major/minor/patch lifecycle

• Importing or exporting skill libraries across projects

• Configuring continuous learning hooks for automatic pattern capture

When NOT to Use

• Task is outside your authorization scope
• You need to implement controls (use implementing-* skills)
• Task is about analysis, not action (use analyzing-* skills)
• You don't have access to target systems
• Task requires compliance expertise (consult professionals)
• Task is about defense, not offense (use defensive skills)

Process

1. Gather requirements and constraints from the user
2. Validate prerequisites (tools, permissions, data)