~cytrogen/gstack

ref: b5b2a15ad2df1d3ea0fe4850fded7a0f23aec08b gstack/test/fixtures/eval-baselines.json -rw-r--r-- 388 bytes
b5b2a15a — Garry Tan fix: pass all LLM evals — severity defs, rubric edge cases, EVALS=1 flag a month ago
                                                                                
1
2
3
4
5
6
7
{
  "command_reference": { "clarity": 4, "completeness": 4, "actionability": 4 },
  "snapshot_flags": { "clarity": 4, "completeness": 4, "actionability": 4 },
  "browse_skill": { "clarity": 4, "completeness": 4, "actionability": 4 },
  "qa_workflow": { "clarity": 4, "completeness": 4, "actionability": 4 },
  "qa_health_rubric": { "clarity": 4, "completeness": 3, "actionability": 4 }
}