eval-author
Use for "help me with my evals", "help me onboard to expand my evals", "what's the state of the eval suite here?", "what happened in this trace?", or requests to create, discover, audit, or improve evaluations. For fresh full workflows, read this skill, show its rendered orientation, and end the turn before repository work. Scoped utilities keep their scope. Explicit full audits quietly check bounded saved context before choosing an introduction. New audits choose task review or add run measurement before checks. Returning audits reuse applicable prerequisites and confirmed Ethos. Separate returning requests get a brief acknowledgment, then continue without another readiness pause. Build first evals from ETHOS.md, work on existing suites, inspect a NeMo Intake run, or derive a trace environment (experimental). Owns the evidence standard for every Eval Author flow. Creating, auditing, and improving evals require confirmed ETHOS.md and do not change the agent implementation.
Informations de source
- Dépôt
- NVIDIA-NeMo/eval-author
- Dernière activité de la source
- 10 novembre 2026 à 20:45
- Langue détectée de SKILL.md
- anglais
- Étoiles
- 12
- Forks
- 1
Options d'installation
Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.
Vérifiez les fichiers source
Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.
Affichage de SKILL.md
| name | eval-author |
|---|---|
| description | Use for "help me with my evals", "help me onboard to expand my evals", "what's the state of the eval suite here?", "what happened in this trace?", or requests to create, discover, audit, or improve evaluations. For fresh full workflows, read this skill, show its rendered orientation, and end the turn before repository work. Scoped utilities keep their scope. Explicit full audits quietly check bounded saved context before choosing an introduction. New audits choose task review or add run measurement before checks. Returning audits reuse applicable prerequisites and confirmed Ethos. Separate returning requests get a brief acknowledgment, then continue without another readiness pause. Build first evals from ETHOS.md, work on existing suites, inspect a NeMo Intake run, or derive a trace environment (experimental). Owns the evidence standard for every Eval Author flow. Creating, auditing, and improving evals require confirmed ETHOS.md and do not change the agent implementation. |