levelup

Extract post-merge learnings from artefact chains and update standards and decision logs.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/heymishy/2x2-v3-28-03-20216 --skill levelup-heymishy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: levelup
Source: https://github.com/heymishy/2x2-v3-28-03-20216/tree/main/.github/skills/levelup
Command: npx skills add https://github.com/heymishy/2x2-v3-28-03-20216 --skill levelup-heymishy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Post-merge learning extraction. Reads the completed artefact chain for a merged story or feature, identifies reusable patterns, decisions, and standards that emerged during delivery, classifies them, and writes them back to the permanent knowledge base. Produces updates to standards/, decisions log, or copilot-instructions.md. Use after /definition-of-done is complete and a PR is merged. Run when someone says "levelup", "extract learnings", "update standards", "what did we learn from this", "pattern extraction", or "post-merge review".

Core Features & Use Cases

  • Extract learnings from artefact chains to improve delivery standards and decision logs.
  • Classify patterns and decisions, generate/update standards, and store artifacts for future reuse.
  • Use Case: After a merged PR with a completed DoD artefact, run levelup to surface repeatable patterns and update the knowledge base.

Quick Start

Run the levelup flow after a merged PR and completed DoD artefact to extract learnings and update standards and decisions.

Frequently Asked Questions about levelup

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

FAQPage Schema
How do I extract post-merge learnings from pull requests to update engineering standards?

To extract post-merge learnings, you analyze the completed artefact chain from discovery to definition-of-done after a PR merges. This classifies reusable patterns and updates your standards, decision logs, and ADRs automatically.

What is post-merge pattern extraction and when should I run it?

Post-merge pattern extraction identifies reusable decisions and standards from delivery artefacts. Run it after a definition-of-done artefact is complete and a PR is merged to surface repeatable patterns for your knowledge base.

How do I update architecture decision records automatically after a feature merge?

Updating architecture decision records happens by reading the merged feature's artefact chain, classifying the decisions made during delivery, and writing new ADRs back to your permanent decisions log and knowledge base.

Does this learning extraction process require a completed definition-of-done artefact?

Yes, this post-merge learning extraction requires a completed definition-of-done artefact and a merged PR. It reads across discovery, decisions, stories, test plans, DOR, and DOD to ensure the full delivery context is available.

What's the best way to capture reusable engineering standards from completed stories?

The best way to capture reusable standards is processing the merged story's artefact chain to identify emerging patterns. This classifies delivery learnings and writes updates directly to your standards directory and copilot-instructions.md.