Learning Loop Skill
Claude Code skill for capturing and codifying learnings before session ends / context lost
melodykoh · AI review on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add melodykoh/learning-loop-skillAbout this skill
Learning-Loop Skill for Claude Code
A two-mode Claude Code skill that catches what your sessions teach you — failed attempts, user corrections, recurring failure modes, judgment shifts — and writes them to the right files before /clear or context compaction destroys the details.
Heads up: this is a personal skill, published in case it's useful. It's shaped by one workflow — a root
~/.claude/CLAUDE.md, per-projectCLAUDE.mdfiles, aMEMORY.md, a personal Judgment Ledger, and Every's/ce-compoundfor code-level capture. If your setup looks roughly like that, the routing will land where you'd expect. If it doesn't, you'll want to read SKILL.md and adapt the destinations.
The Problem
Claude Code sessions accumulate valuable signal — a hypothesis that turned out to be right, a fix you confirmed, a workflow rule you broke and want to encode, a corrected assumption, a recurring mistake you keep making across projects. Most of that gets lost the moment context compacts or you hit /clear.
Claude Code's built-in auto-memory captures quick facts, but it doesn't:
- Distinguish a one-off observation from a pattern you've now hit five times
- Apply quality gates (would this help next time? did you actually verify the fix?)
- Route a process-level rule into
CLAUDE.mdvs. a factual recall intoMEMORY.mdvs. a judgment shift into a content ledger - Surface recurring failure modes that need a structural fix rather than another note
Learning-loop is the structured pass on top of that — invoked explicitly, run by sub-agents so it doesn't eat your main context, and gated so it doesn't pollute your docs with noise.
What It Does
| Mode | When you run it | What it does |
|---|---|---|
/learning-loop scan | Mid-session, before compaction or /clear | Spawns a sub-agent that reads your conversation, extracts raw signals (failed attempts, hypotheses, user corrections, process observations), and writes them to ` |