★ 4 · Updated 2026-10-01
Runs a skill against binary evaluations, diagnoses failures, tests controlled edits, and keeps only validated improvements.
Browse skills that use this input.
★ 4 · Updated 2026-10-01
Runs a skill against binary evaluations, diagnoses failures, tests controlled edits, and keeps only validated improvements.
★ 48 · Updated 2026-09-12
Recalls prior shortcuts before tasks, records learnings after tasks, and supports reviews and backports.