evolve-session-review

Review session-stop evolution to extract transferable learnings via MCP tool calls.

1.4k|14|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/Prismer-AI/PrismerCloud --skill evolve-session-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evolve-session-review
Source: https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/prismer-cloud/claude-code-plugin/skills/evolve-session-review
Command: npx skills add https://github.com/Prismer-AI/PrismerCloud --skill evolve-session-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the evaluation of session-stop evolution to convert insights into reusable improvements.

Core Features & Use Cases

  • Distinguishes transferable learnings from project-specific memory needs.
  • Creates reusable fixes via evolve_create_gene.
  • Logs success/failure with evolve_record and saves context with memory_write when applicable.

Quick Start

Trigger the Stop-hook evolution review for the active session to extract reusable learnings.

Frequently Asked Questions about evolve-session-review

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

FAQPage Schema
How do I automate session review to extract reusable learnings from a stop hook?

Automating session review extracts transferable learnings by evaluating stop-hook evolution signals, distinguishing reusable fixes from project-specific memory needs, and automatically capturing insights for future use.

What is the best way to distinguish transferable fixes from project-specific memory during a session stop?

Distinguishing transferable fixes from project-specific memory requires evaluating session-stop evolution to identify general improvements versus localized context, then routing them to reusable genes or memory writes accordingly.

How does evolve_create_gene work for logging reusable code fixes?

Evolve_create_gene works by taking evaluated session-stop evolution data and converting transferable learnings into reusable fixes, creating genes that encapsulate the insight for future automated application.

Do I need MCP tool calls to automate evolution reviews and memory writes?

You need up to three MCP tool calls to automate evolution reviews, utilizing evolve_create_gene for fixes, evolve_record for logging, and memory_write for saving project-specific context.

Can I use memory_write to save project-specific context when a session stop signals evolution?

You can use memory_write when a session stop signals evolution to save project-specific context, complementing the reusable learnings extracted and logged via the evolution review process.