Agent Learning Layer Triage

Use this skill when a task produces a lesson and the next question is: where should this learning live?

ABVX does not assume the model itself learns. Most useful operational learning belongs in an auditable layer around the model: context, skills, scripts, gates, and evals.

Learning Layers

Classify the candidate into the cheapest durable layer that solves the repeated problem:

1. Leave as prompt/session behavior: one-off correction, low recurrence, no durable value.
2. Memory or context note: stable preference, repo fact, operator convention, or short reminder that should be easy to read and revise.
3. Durable repo doc: stable repo architecture, setup, verification, deployment, or workflow fact that future agents must discover reliably.
4. Checklist: repeated human or agent sequence where order matters but no portable behavior layer is needed yet.
5. SKILL.md: reusable behavior with a clear trigger, action rules, anti-patterns, and verification discipline.
6. Script or tool: deterministic repeated step where code is more reliable than prose.
7. Eval or golden fixture: behavior must be regression-tested, especially after a bug, review failure, or model drift.
8. Reject / park: plausible but overfit, too broad, not validated, duplicative, or unsafe.