agent-evolution

Extract session discoveries and append them to SKILL.md KNOWLEDGE sections.

7|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/rloisell/rl-agents-n-skills --skill agent-evolution-rloisell
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-evolution
Source: https://github.com/rloisell/rl-agents-n-skills/tree/main/agent-evolution
Command: npx skills add https://github.com/rloisell/rl-agents-n-skills --skill agent-evolution-rloisell

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Development sessions generate valuable discoveries that are often lost or siloed; agent-evolution ensures past fixes, causal learnings, and patterns are surfaced before work begins and captured after sessions so the team steadily improves its shared skill library.

Core Features & Use Cases

  • Pre-session retrieval: Locate and surface past KNOWLEDGE entries relevant to a branch or feature so context is available before work starts.
  • Automated knowledge capture: Read WORKLOG, CHANGES, and COMMANDS files and append concise, timestamped entries to the appropriate SKILL.md *_KNOWLEDGE sections.
  • Shared-skill promotion & audits: Detect cross-agent patterns for promotion to shared skills, flag oversized SKILL.md files, and maintain an evolution log of all changes.
  • Governance & traceability: Enforces entry formats, line-count thresholds, and records session summaries in references/evolution-log.md for historical review.

Quick Start

Run agent-evolution at session end to scan the session WORKLOG/CHANGES/COMMANDS, append standardized KNOWLEDGE bullets to relevant SKILL.md files, and write a summary entry to references/evolution-log.md.

Frequently Asked Questions about agent-evolution

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

FAQPage Schema
How do I capture session discoveries and append them to SKILL.md knowledge sections automatically?

To capture session discoveries automatically, agent-evolution reads WORKLOG, CHANGES, and COMMANDS files, then appends concise timestamped entries to the appropriate SKILL.md KNOWLEDGE sections. This ensures past fixes and patterns are retained for future pre-session retrieval.

What is the best way to surface relevant agent knowledge before starting a development session?

Surface relevant agent knowledge before a session by running pre-session retrieval. This mechanism locates and extracts past KNOWLEDGE entries from SKILL.md files that match your branch or feature, providing immediate context before work begins.

How do I audit SKILL.md files for oversized content and cross-agent patterns?

Audit SKILL.md files by detecting cross-agent patterns for promotion to shared skills and flagging oversized files that exceed line-count thresholds. The process maintains governance by enforcing entry formats and recording summaries in an evolution log.

Can I use agent-evolution for end-of-session reviews without external dependencies?

Yes, you can perform end-of-session reviews without external dependencies. agent-evolution operates independently to scan session files, append standardized knowledge bullets to SKILL.md files, and write summary entries to references/evolution-log.md.

Why does my agent knowledge management process lose past fixes and causal learnings?

Agent knowledge management loses past fixes when development sessions generate discoveries that remain siloed. agent-evolution solves this by extracting session discoveries and appending them to SKILL.md files, ensuring the shared skill library steadily improves.

When do I need to promote cross-agent patterns to shared skills?

Promote cross-agent patterns to shared skills when recurring discoveries appear across multiple sessions. agent-evolution detects these patterns during end-of-session audits and appends them to shared SKILL.md files while recording the change in an evolution log.