memory-proposer

Detect recurring memory case patterns and propose draft PRs updating SKILL.md learned-pattern sections.

Updated Mar 9, 2026

Search Tags:#memory #clustering #git-worktree #draft-pr #pattern-detection #learned-patterns

Ready to run

npx skills add https://github.com/RafayelGardishyan/rafayels-marketplace --skill memory-proposer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-proposer
Source: https://github.com/RafayelGardishyan/rafayels-marketplace/tree/main/plugins/rafayels-engineering/.opencode/skills/memory-proposer
Command: npx skills add https://github.com/RafayelGardishyan/rafayels-marketplace --skill memory-proposer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scipy, numpy, and includes scripts (resource) and references (resource) components.

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>.

Frequently Asked Questions about memory-proposer

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

FAQPage Schema

How do I append learned patterns to skill files without modifying agent code?▼

To append learned patterns safely, this Skill generates draft PRs that restrict edits to the "Learned Patterns" section of SKILL.md files. It isolates changes to skills or references directories, ensuring agent code remains untouched.

How does pattern detection from memory cases work for generating skill updates?▼

Pattern detection works by clustering active and promoted memory cases using embedding similarity. It identifies recurring patterns and maintains identity stability across re-runs by matching new clusters to existing ones via centroid similarity.

Can I automatically propose git-worktree changes as draft PRs for detected patterns?▼

Yes, you can propose detected patterns as draft PRs using content-hash branch names. The Skill enforces safety guardrails by always creating draft PRs, ensuring proposed updates are reviewable before merging.

Do I need scipy and numpy to cluster memory cases by embeddings?▼

Yes, scipy and numpy are required dependencies for clustering memory cases by embeddings. These libraries provide the numerical and scientific computing foundation needed for calculating embedding similarity and centroid matching.

What is the best way to review detected memory patterns before creating a draft PR?▼

The best way to review detected memory patterns is using the list command. After detecting clusters with the detect command, you can review them and then generate a draft PR for a chosen pattern with the propose command.

When should I not use automated draft PRs for skill knowledge capture?▼

You should not use automated draft PRs if you need immediate changes to skill files, as they are created as drafts requiring manual review. Additionally, edits are restricted only to the "Learned Patterns" section of SKILL.md files.