← ClaudeAtlas

learnlisted

Use when the user says 'learn!', 'capture this', 'update the skill', 'remember this for next time', or when a session surfaces a non-obvious pitfall, a doc-vs-reality gap, or a missing step in a skill/rule that was in use. Routes session learnings back into this repo's persistent guidance — skills/*/SKILL.md (+ references/), rules/coding-*.md, CLAUDE.md — rather than auto-memory. Automatically identifies which skills and rules were loaded during the session, checks for existing coverage (especially fabric-gotchas), verifies the learning against official docs before encoding it, proposes the edit at the right heading as a diff for approval, then hands off to /commit. Never edits silently, never writes domain knowledge to memory.
wardawgmalvicious/claude-config · ★ 2 · AI & Automation · score 75
Install: claude install-skill wardawgmalvicious/claude-config
# Learn: capture session learnings into skills and rules Turn something discovered during this session into a durable, verified edit to the guidance that *should* have covered it. The goal is that the next session never has to rediscover it. This skill **proposes**; it does not commit. Edits land only after the user approves the diff, and committing is handed to `/commit`. ## Step 1 — Identify what was learned Reflect on the session, not just the last message. Candidate learnings: - A skill or rule said X; reality was Y (doc-vs-reality gap). - A step was missing and cost debugging time. - An error message whose cause was non-obvious. - A constraint / limit / version change not documented anywhere here. - A user correction that reveals a general principle. For each candidate, state in one or two sentences: **problem → root cause → correct approach → generalization**. Drop anything that is one-off, already obvious from the code, or only matters to this conversation. Confirm the list with the user before proceeding if it contains more than one item or you're unsure which matters. ## Step 2 — Identify which guidance was in use (automatic) Do **not** ask the user which skill was used. Reconstruct it: 1. **Skills invoked this session** — every `Skill` tool call and every skill whose content appears in context (the `<command-name>` / loaded-skill blocks). Record the `name:` of each. 2. **Rules auto-loaded** — any `rules/coding-*.md` content present in context, trig