- _templates/eval-results.md: new Transferable Lessons section (2-5 generalizable
bullets + mandatory methodology-note promotion check) and Proposed Changes (Loop
Inputs) section (concrete candidate wording, tagged by target surface and measured
gap — the tuning-loop handoff artifact).
- os-vault-write-eval-baseline-grid-results.md: backfilled to the new template.
Four transferable lessons (headline: persistence evals need a destination axis,
not just a trigger axis) and four verbatim WS2 loop-input candidates: destination
ladder wording, query-side triggers (no eval coverage yet), query-first
update-vs-create rule, type-misfit routing. No os-vault skill/hook surface touched
— applying candidates starts the wording loop.
- eval-methodology-ladder.md: documented the lesson-promotion pattern from the
methodology side.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Jared Swanson