ML Retain — AI skill for Claude Code
Capture session learnings in documentation (Meta-Loop Step 4).
How to install ML Retain
Installs to ~/.claude/skills/jpavley-meta-loop-ios-ml-retain/SKILL.md
mkdir -p ~/.claude/skills/jpavley-meta-loop-ios-ml-retain && curl -fsSL https://raw.githubusercontent.com/jpavley/meta-loop-ios/HEAD/commands/ml-retain.md -o ~/.claude/skills/jpavley-meta-loop-ios-ml-retain/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What ML Retain does
description: Capture session learnings in documentation (Meta-Loop Step 4)
Meta-Loop: Learning Retention
Capture session learnings in documentation before clearing context.
**Modes:** Plan Mode → Agent Mode
Prerequisites
This skill implements **Step 4** of the Meta-Loop process defined in `skills/meta-loop-methodology/SKILL.md`.
Use this after a successful implementation pass (`/ml-impl` review passed).
Phase 1: Plan (Plan Mode)
**Enter plan mode** and create a plan
Alternatives in AI
- Invisible Dots — Open-source, self-hosted alternative to OpenAI Dots, Meta Muse, Grok Bot, Manus Cue and Claude Cowork 31.8k ★
- Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
- Open Dots — Open-source, self-hosted AI agent workspace and alternative to OpenAI Dots, Meta Muse, Grok Bot, Instinct, Man 5.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Development Analyst
You are an expert in analyzing development sessions and optimizing AI-human collaboration. Your task is to ref
Animated Drawing
Animate a SUPPLIED drawing/photo of a character with real motion capture (Meta AnimatedDrawings) → raster GIF/
Metaharness
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MC
ML Impl
Full implementation loop - plan, write, and review code (Meta-Loop Steps 3.1-3.4)
ML Setup
Scaffold project directories and starter files for the meta-loop workflow
Devloop
A guard-railed, closed-loop workflow for AI coding agents: live state bus + execution-level hard intercepts fo
Related Agents
Wiki Add Task
Use this agent when capturing ad-hoc ideas, bugs, tasks, or notes into the vault during automated maintenance
Ami Doc Architect
Master documentation orchestrator. Invoke when architecting, synchronizing, or maintaining project docs and se
Learning Scribe
Gate-7 capture agent. Converts every deep-review fix or observable incident into a durable docs/learnings/ ent