OpenAgentSkill
GitHub200+

Vorinstallations-Eval

clean-room-review Eval-Bericht.

Eine maschinenlesbare Installationsentscheidung für Agents: Task-Fit, Trust Score, Audit Score, Installationssicherheit, Berechtigungsumfang und ein konkreter Validierungsplan vor dem Einsatz im Workspace.

Prüfung nötigMittleres RisikoPrüfen Richtlinie
63
Eval-Bericht
64
Vertrauen
71
Audit
51
Agent-Sicherheit

Manuelle Prüfung

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

Erforderliche Gates

Prüfungen, die ein Agent vor der Installation bestehen muss

JSON öffnen

Aufgabenpassung

84

Bestanden

Task wording matches this skill metadata.

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

Installationspfad

92

Bestanden

Install handoff is available.

  • npx skills add linux-engineering-tools/community --skill clean-room-review

Sicherheit des Installationsbefehls

92

Bestanden

Standard-Paket- oder Laufzeit-Installationspfad

  • npx skills add linux-engineering-tools/community --skill clean-room-review

Vertrauenswert

64

Warnung

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

  • Manuelle Prüfung
  • 11 GitHub-Stars
  • Apache-2.0

Audit-Score

71

Warnung

Prüfung nötig

  • The file excerpt ends mid-sentence at 'If that'; if the repository SKILL.md is actually truncated, the final sentence should be completed and the file re-verified.

Agent-Sicherheitsprüfung

51

Warnung

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The file excerpt ends mid-sentence at 'If that'; if the repository SKILL.md is actually truncated, the final sentence should be completed and the file re-verified.

Lizenzklarheit

86

Bestanden

Apache-2.0

  • Apache-2.0

Berechtigungsumfang

86

Bestanden

Dateisystem- oder Dokumentzugriff

  • Browser automation: medium
  • Network access: medium
  • Filesystem access: medium

Validierungsplan

Was der Agent als Nächstes tun sollte

  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.

Nicht verwenden, wenn

Bedingungen für eine andere Skill

  • Teams, die ein vom Anbieter unterstütztes SLA benötigen
  • production agents without a repository review
  • Low GitHub adoption signal
  • The file excerpt ends mid-sentence at 'If that'; if the repository SKILL.md is actually truncated, the final sentence should be completed and the file re-verified.
  • No OpenAgentSkill engagement data yet
  • The skill instructs the agent to 'close or convert' flagged issues/PRs without explicitly checking maintainer authorization or requiring human-in-the-loop confirmation.

Unterstützende Prüfungen

Vertrauenssignale hinter der Entscheidung

README/SKILL.md-Vollständigkeit

Warnung

76

Öffentliche Metadaten benötigen mehr README/SKILL.md-Kontext

Aktuelle Wartung

Bestanden

88

1 Monate seit dem letzten Push

Alternativen verfügbar

Bestanden

82

Alternative skills are available for comparison.