draft-distill-proposals

Community

Turn PR diffs into staged learning proposals

Authorkapilvirenahuja
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It analyzes a merged PR diff (optionally with related STM evidence) to detect real learning signals, then produces lightweight, staged proposals so future work can avoid repeating mistakes.

Core Features & Use Cases

  • Diff-to-proposal learning extraction: Detects semantic learning signals from implementation changes and classifies them into targeted updates.
  • STM-evidence-aware confidence: Reads available issue evidence (enhance/fix-it artifacts) to raise or lower confidence and prioritize the strongest learnings.
  • Staged proposals for review: Writes proposals.yaml only to the issue’s STM evidence/distill area, enabling optional human review without updating product LTM.

Quick Start

Use the draft-distill-proposals skill to analyze a merged PR diff along with any available issue STM evidence and generate up to two staged proposals in proposals.yaml for human review.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: draft-distill-proposals
Download link: https://github.com/kapilvirenahuja/garura/archive/main.zip#draft-distill-proposals

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.