diagnose-benchmark-failure
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.
70
Quality
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Securityby
Passed
No findings from the security scan
Loading evals
- Repository
- korchasa/flowai-plugins
- Commit
b4ba256
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.