document-learnings

Document Max for Live learnings in the canonical Max4Live-MCP knowledge repository.

Updated Aug 9, 2026
One-click install
npx skills add https://github.com/CooperNederhood/Ableton-Agent-App --skill document-learnings-coopernederhood
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: document-learnings
Source: https://github.com/CooperNederhood/Ableton-Agent-App/tree/main/.github/skills/document-learnings
Command: npx skills add https://github.com/CooperNederhood/Ableton-Agent-App --skill document-learnings-coopernederhood

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Max for Live development knowledge is easily lost after a patching session ends. This Skill captures what was learned about a Max for Live patch or topic and stores it in a structured, validated, and ingestible format inside the canonical Max4Live-MCP knowledge repository. ## Core Features & Use Cases - Structured Learning Documents: Creates a patch-learnings.md file with YAML frontmatter (type, key_objects, complexity, source) plus sections for description, implementation details, object roles, lessons learned, and anti-patterns. - Visual Documentation: Captures patching-view and presentation-view screenshots and copies the saved .amxd device file when available. - Validation and Ingestion: Runs the ingest_learning.py script with --validate before ingesting the learning into the max_knowledge tree. - Use Case: After building a Max for Live MIDI effect, use this Skill to record the signal flow, object roles, and gotchas so the knowledge is searchable in future sessions. ## Quick Start Document what we learned from this Max for Live patch and ingest it into the Max4Live-MCP knowledge repository.

Frequently Asked Questions about document-learnings

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

FAQPage Schema
How do I document Max for Live patch learnings?▼

Create a patch-learnings.md file in the max_knowledge/m4l-learnings directory with YAML frontmatter and sections for description, implementation details, object roles, lessons learned, and anti-patterns. Then validate and ingest it with the ingest_learning.py script.

What frontmatter fields are required for a Max for Live learning document?▼

The learning document must include YAML frontmatter with type, key_objects, complexity, and source fields. The body then follows with description, implementation details, an Object Roles table, lessons learned, and anti-patterns sections.

How do I validate and ingest a learning into the max_knowledge repository?▼

Run python3 ingest_learning.py with the learning file path and the --validate flag first, then run it again without the flag to ingest. Both commands use the script located in the Max4Live-MCP repository's scripts directory.

What screenshots are needed for Max for Live documentation?▼

Capture both a patching-view.jpg and a presentation-view.jpg in a patch-screenshots folder. Take screenshots last because they consume substantial context, and copy the saved .amxd file when available.

Where should Max for Live learnings be stored?▼

All output goes in the canonical checkout at $MAX4LIVE_MCP_ROOT/max_knowledge/m4l-learnings/<topic-or-patch-name>/. Never create a second max_knowledge tree inside the ableton-agent-app repository.