evolve

Analyze Claude Code session transcripts to recommend skill, agent, and workflow improvements.

2|Updated Mar 16, 2026
One-click install
npx skills add https://github.com/billbuchanan-code/claude-code-power-setup --skill evolve-billbuchanan-code
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evolve
Source: https://github.com/billbuchanan-code/claude-code-power-setup/tree/main/skills/evolve
Command: npx skills add https://github.com/billbuchanan-code/claude-code-power-setup --skill evolve-billbuchanan-code

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes recent Claude Code session transcripts and project activity to identify recurring patterns and recommends new skills, agents, or workflow improvements that save time.

Core Features & Use Cases

  • Analyze patterns across session transcripts, file edits, and tool usage to surface repeatable workflows.
  • Propose concrete evolutions such as new skills, agents, or automation commands to accelerate typical tasks.
  • Example: generate a top-priority skill that automates a frequent debugging or code-review loop.

Quick Start

Run /evolve to generate pattern-based recommendations for skills, agents, or workflow improvements.

Frequently Asked Questions about evolve

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

FAQPage Schema
How do I analyze Claude Code session transcripts to identify recurring workflow patterns?

To identify recurring workflow patterns, the tool scans local JSONL session files and shell histories to cluster frequent tool usage and file edits, surfacing repeatable actions for automation.

What is the best way to generate new skills and agents from existing project activity?

Generating new skills and agents from project activity involves ranking detected session patterns by frequency and proposing concrete SKILL or AGENT files that automate those high-priority recurring tasks.

Can I automate frequent debugging loops by creating rules from command histories?

Yes, you can automate frequent debugging loops by analyzing command histories to detect repetitive shell actions, then generating concrete RULE recommendations and optional automation files to streamline those tasks.

Does session analysis work with local JSONL files and shell histories without external dependencies?

Session analysis works directly with local JSONL files and shell histories without requiring external dependencies, relying entirely on local storage to extract and cluster project activity data.

How do I turn detected session patterns into concrete workflow improvements?

You turn detected session patterns into workflow improvements by clustering transcript data, ranking the identified behaviors, and generating actionable SKILL, AGENT, or RULE recommendations to accelerate typical tasks.