memory-proposer

What problem does it solve?

Detects recurring patterns in the memory case bank and proposes skill updates as reviewable draft PRs, enabling knowledge capture and reuse without risking automatic changes to agent or skill code.

Core Features & Use Cases

• Detects clusters of successful cases by embedding similarity and surfaces recurring patterns.
• Generates draft PRs that append learned patterns to the target skill's SKILL.md under a dedicated "Learned Patterns" section.
• Maintains identity stability by matching new clusters to existing patterns via centroid similarity and using content-hash branch names.
• Designed to be used alongside the memory skill to continually evolve capabilities while preserving system safety.

Quick Start

Detect pattern clusters with memory-proposer detect, review them with memory-proposer list, and generate a draft PR for a chosen pattern with memory-proposer propose <id> --target-skill <skill>.