OpenAgentSkill
GitHub200+

Évaluation avant installation

competitor-ad-research Rapport d’évaluation.

Une décision d’installation lisible par machine pour les Agents : adéquation à la tâche, Trust Score, Audit Score, sécurité d’installation, surface de permissions et plan de validation concret avant de toucher l’espace de travail.

Revue nécessaireRisque moyenRevoir Politique
68
Rapport d’évaluation
68
Confiance
73
Audit
57
Sécurité Agent

Revue manuelle

Test manually in an isolated workspace and compare against safer alternatives.

Gates requis

Vérifications qu’un Agent doit réussir avant installation

Ouvrir JSON

Adéquation à la tâche

94

Validé

Task wording matches this skill metadata.

  • Evaluate competitor-ad-research before installing it in an agent workflow
  • Recherche
  • Research agents workflows; Claude Code teams; builders willing to evaluate younger projects

Chemin d’installation

92

Validé

Install handoff is available.

  • npx skills add sandbaseai/sandbase-skills --skill competitor-ad-research

Sécurité de la commande d’installation

92

Validé

Chemin d’installation standard de package ou runtime

  • npx skills add sandbaseai/sandbase-skills --skill competitor-ad-research

Score de confiance

68

Avertissement

Potentially useful, but at least one trust signal needs human inspection.

  • Revue manuelle
  • 58 stars GitHub
  • Apache-2.0

Score d’audit

73

Avertissement

Revue nécessaire

  • The API map is minimal and relies entirely on sandbase_describe_tool for parameter details, which is acceptable but could be more informative.

Contrôle de sécurité Agent

57

Avertissement

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The API map is minimal and relies entirely on sandbase_describe_tool for parameter details, which is acceptable but could be more informative.

Clarté de licence

86

Validé

Apache-2.0

  • Apache-2.0

Surface de permissions

74

Avertissement

network or browser access, database access

  • Network access: medium
  • Database access: medium

Plan de validation

Ce que l’Agent doit faire ensuite

  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.

Ne pas utiliser quand

Conditions exigeant une autre skill

  • Équipes qui nécessitent un SLA soutenu par le fournisseur
  • production agents without a repository review
  • The API map is minimal and relies entirely on sandbase_describe_tool for parameter details, which is acceptable but could be more informative.
  • No explicit limitations or edge cases are documented in SKILL.md, such as rate limits or data availability constraints.
  • Quality score needs review
  • GitHub adoption: 58 GitHub stars

Vérifications complémentaires

Signaux de confiance derrière la décision

Complétude README/SKILL.md

Avertissement

76

Les métadonnées publiques nécessitent davantage de contexte README/SKILL.md

Maintenance récente

Validé

88

2 mois depuis le dernier push

Alternatives disponibles

Validé

82

Alternative skills are available for comparison.