mirror of
https://github.com/addyosmani/agent-skills.git
synced 2026-08-12 18:07:26 +02:00
The optimization workflow lists five steps but only documents three; VERIFY has no section of its own. Add it: re-measure under baseline conditions, change one thing at a time, beat run-to-run variance, and keep only what pays for itself. Neutral and test-breaking results revert. Also log every attempt, including the reverted ones, so a discarded idea does not get re-run later. Add the corresponding Common Rationalizations, Red Flags, and Verification entries.