diagnose-benchmark-failure

SKILLWorkflowcommunity
v0.0.0korchasaUnknownUpdated 1d agoSource →

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

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
3Repo stars
1Clients
1Formats
1d agoLast update
Skill
Authorkorchasa
Version0.0.0
LicenseUnknown
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

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.

Keywords
skillclaude