/learn
Use when the user says /learn or asks to save this lesson.
$ npx -y skills add tigerless-labs/autoharness --skill learn --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/learn
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user says /learn or asks to save this lesson.
SKILL.md
learn.SKILL.mdname: learn description: Use when the user says /learn or asks to save this lesson. category: general
Learn: distill this session into the skill library
Review the conversation so far and distill what is worth keeping — through the standard proposal chain, never by writing files.
1. Identify class-level, reusable lessons: corrected approaches, non-trivial techniques, durable user preferences. Skip one-off narratives and environment-specific failures. 2. Compare first: read the injected skill index; if an existing skill covers the topic, prefer a `patch`/`update` over creating a near-duplicate. 3. Reconcile old with new: when a lesson supersedes an earlier rule, search the managed skill trees for contradicting statements and stage updates so the new version wins everywhere. 4. Stage every change exclusively via the `stage_skill` tool, one intent per lesson, with `reason` and a verbatim `evidence` quote from this session. The deterministic promoter validates and lands; rejects are reported at the next session start.
If nothing meets the bar, say so and stage nothing.
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.