benbrownandClaude Fable 5 3946438fd6 skill: attempt mode points at explain for the next hypothesis ...

The attempt-mode guide predates crates/explain and stopped at the ROI
report. It now names the post-verdict step: run just explain on every
rejection before forming the next hypothesis — below-bar, null, and
regression are three different next moves the verdict string alone does
not distinguish. Advisory framing preserved (quote the record, not the
inferences). Mirror regenerated.

Verify mode needs nothing: consumer repos have no ledger, and its
read-it-honestly table already encodes the same narrative doctrine.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-20 10:05:41 -04:00

..

assets

skill: make the peltier skill consumable across agent harnesses

2026-07-15 11:59:26 -04:00

references

skill: attempt mode points at explain for the next hypothesis

2026-07-20 10:05:41 -04:00

scripts

skill: cross-OS preflight — ps1 entry point, one CI-enforced contract

2026-07-16 08:15:43 -04:00

SKILL.md

skill: make the sh-vs-ps1 dispatch rule explicit

2026-07-16 08:32:22 -04:00