OpenAgentSkill
GitHub200+

Évaluation avant installation

quantitative-screening 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
69
Rapport d’évaluation
71
Confiance
76
Audit
52
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

84

Validé

Task wording matches this skill metadata.

  • Evaluate quantitative-screening before installing it in an agent workflow
  • data-analysis
  • Research agents workflows; Claude Code teams; builders willing to evaluate younger projects

Chemin d’installation

92

Validé

Install handoff is available.

  • npx skills add agentii-ai/agentii-investment-intelligence --skill quantitative-screening

Sécurité de la commande d’installation

92

Validé

Chemin d’installation standard de package ou runtime

  • npx skills add agentii-ai/agentii-investment-intelligence --skill quantitative-screening

Score de confiance

71

Avertissement

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

  • Revue manuelle
  • 203 stars GitHub
  • Apache-2.0

Score d’audit

76

Avertissement

Revue nécessaire

  • Financial research output is not financial advice; require human review before any live investment decision

Contrôle de sécurité Agent

52

Avertissement

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • Financial research output is not financial advice; require human review before any live investment decision

Clarté de licence

86

Validé

Apache-2.0

  • Apache-2.0

Surface de permissions

74

Avertissement

filesystem or document access, database access

  • Browser automation: medium
  • Network access: medium
  • Filesystem 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 skill references contracts/preflight.md and contracts/x-agentii-trace-header.md which are not included in the submission; ensure these are available in the repository.
  • Financial research output is not financial advice; require human review before any live investment decision
  • The allowed_tools list includes only three tools, but the methodology mentions search_institutional_holdings and search_insider_trades as signal inputs; clarify whether these are intended to be used or if they are optional external references.
  • Financial research output is not financial advice; require human review before any live investment decision.

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

1 mois depuis le dernier push

Alternatives disponibles

Validé

82

Alternative skills are available for comparison.