agent-eval
Use when installing or using @primer/agent-eval, designing agent evaluations, creating benchmarks, experiments, scenarios, checks, judges, or treatments, and running, planning, sharding, or interpreting evaluations with the agent-eval CLI.
Datos de origen
- Repositorio
- primer/agent-eval
- Última actividad en el origen
- 20 de octubre de 2026 a las 16:49
- Idioma detectado de SKILL.md
- inglés
- Estrellas
- 2
- Forks
- 0
Opciones de instalación
De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.
Revisa los archivos de origen
Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.
Mostrando SKILL.md
SKILL.md
Instrucciones de origen · Vista previa de solo lectura- name
- agent-eval
- description
- Use when installing or using @primer/agent-eval, designing agent evaluations, creating benchmarks, experiments, scenarios, checks, judges, or treatments, and running, planning, sharding, or interpreting evaluations with the agent-eval CLI.
# agent-eval
Read `node_modules/@primer/agent-eval/docs/AGENTS.md` in the evaluation project,
then load only the references needed for the task. The installed package docs
are the source of truth for its version; do not use docs from a different version.
If the package is not installed, install it with
`npm install --save-dev @primer/agent-eval` (or the project's package manager).
If an older package does not include docs, ask the user before upgrading it;
otherwise use that version's README, package types, and
`npx agent-eval <command> --help` without assuming newer APIs are available.
To load these docs without installing this skill, run
`npx agent-eval agent setup` from the project's root. It adds guidance to the
project's agent instructions.
Ver en GitHub