evolve

Consolidate lessons and decisions into reusable SKILL.md entries.

16|3|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/YehudaFrankel/clankbrain --skill evolve-yehudafrankel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evolve
Source: https://github.com/YehudaFrankel/clankbrain/tree/main/.claude/skills/evolve
Command: npx skills add https://github.com/YehudaFrankel/clankbrain --skill evolve-yehudafrankel

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically consolidates scattered experiential knowledge from lessons and decisions into reusable, codified skills, reducing duplication and accelerating learning loops.

Core Features & Use Cases

  • Analyze memory files (.claude/memory/lessons.md and .claude/memory/decisions.md) to identify recurring patterns.
  • Compare against existing skills under .claude/skills/ and propose new SKILL.md entries or updates to existing skills.
  • Maintain traceability of improvements by documenting patches and decisions for future sessions.

Quick Start

Summarize the most recent lessons and identify patterns to propose or create new skills.

Frequently Asked Questions about evolve

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I consolidate recurring lessons and decisions into reusable skills?

Consolidating recurring lessons into reusable skills involves analyzing memory files like lessons.md and decisions.md to identify patterns, then generating or updating SKILL.md entries under .claude/skills to codify experiential knowledge automatically.

What is the best way to automate turning repeated development patterns into new skills?

The best way to automate repeated development patterns into skills is by scanning .claude/memory/ files during learning sessions to detect recurring decisions, then proposing new SKILL.md entries or updating existing meta files to reflect improvements.

How does identifying recurring patterns from memory files improve the learning loop?

Identifying recurring patterns from memory files improves the learning loop by capturing scattered experiential knowledge, reducing duplication, and writing it into structured SKILL.md entries that accelerate future development sessions.

How do I update existing skills based on newly documented decisions?

To update existing skills based on newly documented decisions, compare recent memory entries against current SKILL.md files, then patch the existing skills and update meta files to maintain traceability of the improvements.

When do I need to create new SKILL.md entries versus updating existing ones?

You create new SKILL.md entries when analysis reveals novel patterns not covered by current skills, and update existing ones when new memory file lessons enhance or modify already codified behaviors.

Can I trace skill improvements back to original lessons and decisions?

You can trace skill improvements back to original lessons and decisions by documenting patches within the meta files during the consolidation process, ensuring future sessions can reference the history of improvements.