OpenAgentSkill
GitHub200+

Evaluación previa a la instalación

recurring-character-diary-comic Informe de evaluación.

Una decisión de instalación legible por máquina para Agents: afinidad con la tarea, Trust Score, Audit Score, seguridad de instalación, superficie de permisos y un plan de validación concreto antes de tocar el espacio de trabajo.

FallidoRiesgo altoBloquear Política
69
Informe de evaluación
72
Confianza
76
Auditoría
56
Seguridad de Agent

do not auto install

Install path: No install command or repository handoff is available.

Controles obligatorios

Comprobaciones que un Agent debe superar antes de instalar

Abrir JSON

Ajuste de tarea

84

Aprobado

Task wording matches this skill metadata.

  • Evaluate recurring-character-diary-comic before installing it in an agent workflow
  • Seguridad
  • Security and compliance workflows; Claude Code teams; builders willing to evaluate younger projects

Ruta de instalación

20

Fallido

No install command or repository handoff is available.

Seguridad del comando de instalación

92

Aprobado

Ruta estándar de paquete o instalación en tiempo de ejecución

Puntuación de confianza

72

Advertencia

Good trust signals with a few areas worth checking before rollout.

  • Lista sólida
  • 148 estrellas de GitHub
  • Apache-2.0

Puntuación de auditoría

76

Advertencia

Requiere revisión

  • The provided SKILL.md excerpt is truncated mid-sentence, so the complete SKILL.md could not be fully verified from the excerpt alone; the accompanying README and references suggest the full skill is comprehensive.

Control de seguridad de Agent

56

Advertencia

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • The tracked source changed or could not be synchronized. Review the current source before installing.

Claridad de licencia

86

Aprobado

Apache-2.0

  • Apache-2.0

Superficie de permisos

74

Advertencia

filesystem or document access, database access

  • Network access: medium
  • Filesystem access: medium
  • Database access: medium

Plan de validación

Qué debe hacer el Agent después

  1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
  2. 2Install in an isolated workspace or sandbox with no production secrets available.
  3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
  4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
  5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

No usar cuando

Condiciones que requieren otra skill

  • Equipos que necesitan un SLA con soporte del proveedor
  • production agents without a repository review
  • The provided SKILL.md excerpt is truncated mid-sentence, so the complete SKILL.md could not be fully verified from the excerpt alone; the accompanying README and references suggest the full skill is comprehensive.
  • The tracked source changed or could not be synchronized. Review the current source before installing.
  • The compositor script processes manifest-supplied paths and hashes; while it has dry-run validation, users should ensure manifests come from trusted local sources and that output paths are explicitly reviewed to avoid unintended file overwrites.
  • Quality score needs review

Comprobaciones de apoyo

Señales de confianza detrás de la decisión

Completitud de README/SKILL.md

Aprobado

86

Los metadatos incluyen suficiente contexto de uso y flujo de trabajo

Mantenimiento reciente

Aprobado

88

1 meses desde el último push

Alternativas disponibles

Aprobado

82

Alternative skills are available for comparison.