Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or g
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.