- mizan-authoringbyghchinoy
Author metric-template packs for Mizan from an agent: scaffold a pack, create…
- hermes-rubricbyhermes-labs-ai
Assess named artifacts with evidence-cited Hermes Rubric results and explicit coverage limits.
- modo-ai-skillsbymodo-learning
Assess how well you work with AI against Modo's public rubric: scored prompt by prompt, with a level, confidence, run…
- mizan-evalbyghchinoy
Run Mizan evaluations from an agent: score a single response or compare two responses against a metric template via the…