OpenAgentSkill
GitHub200+

Vorinstallations-Eval

better-typography 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
69
Eval-Bericht
68
Vertrauen
75
Audit
55
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 better-typography before installing it in an agent workflow
  • Coding-Agents
  • Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects

Installationspfad

92

Bestanden

Install handoff is available.

  • npx skills add boraoztunc/skills --skill better-typography

Sicherheit des Installationsbefehls

92

Bestanden

Standard-Paket- oder Laufzeit-Installationspfad

  • npx skills add boraoztunc/skills --skill better-typography

Vertrauenswert

68

Warnung

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

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

Audit-Score

75

Warnung

Prüfung nötig

  • SKILL.md metadata lacks YAML tags/frameworks fields; not required, but reduces discoverability in some agents.

Agent-Sicherheitsprüfung

55

Warnung

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • SKILL.md metadata lacks YAML tags/frameworks fields; not required, but reduces discoverability in some agents.

Lizenzklarheit

86

Bestanden

Apache-2.0

  • Apache-2.0

Berechtigungsumfang

72

Warnung

filesystem or document access, network or browser access

  • 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
  • SKILL.md metadata lacks YAML tags/frameworks fields; not required, but reduces discoverability in some agents.
  • No explicit 'Limitations' section describing when the skill should not be applied or that it only makes recommendations and does not execute code.
  • The skill references sibling skills by name (better-writing, better-accessibility, better-layout, better-colors) without describing fallback behavior when those skills are unavailable.
  • The provided SKILL.md excerpt ends mid-sentence at '### 6. Heading Siz'; if the actual file is truncated, it would be a critical completeness issue, but based on the repository structure this appears to be an excerpt artifact.

Unterstützende Prüfungen

Vertrauenssignale hinter der Entscheidung

README/SKILL.md-Vollständigkeit

Bestanden

86

Metadaten enthalten ausreichend Nutzungs- und Workflow-Kontext

Aktuelle Wartung

Bestanden

88

2 Monate seit dem letzten Push

Alternativen verfügbar

Bestanden

82

Alternative skills are available for comparison.