OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

dashboard-builder Laporan evaluasi.

Keputusan pemasangan yang dapat dibaca mesin untuk Agent: kecocokan tugas, Trust Score, Audit Score, keamanan pemasangan, cakupan izin, dan rencana validasi konkret sebelum skill menyentuh workspace.

GagalRisiko tinggiBlokir Kebijakan
73
Laporan evaluasi
74
Kepercayaan
81
Audit
57
Keamanan Agent

do not auto install

Audit score: Risky

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate dashboard-builder before installing it in an agent workflow
  • Desain dan kreatif
  • Web scraping workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add winstonkoh87/Athena-Public --skill dashboard-builder

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add winstonkoh87/Athena-Public --skill dashboard-builder

Skor kepercayaan

74

Peringatan

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

  • Shortlist kuat
  • 592 star GitHub
  • MIT

Skor audit

81

Gagal

Berisiko

  • Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required

Gerbang keamanan Agent

57

Gagal

This skill should not be selected by an agent without explicit human security review.

  • Do not auto-install. Inspect the source, dependencies, and permission surface first.
  • Audit risk exceeds the requested agent policy

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

72

Peringatan

filesystem or document access, network or browser access

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

Rencana validasi

Langkah Agent berikutnya

  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.

Jangan gunakan ketika

Kondisi yang membutuhkan skill lain

  • Tim yang membutuhkan SLA dengan dukungan vendor
  • production agents without a repository review
  • The skill claims 'no server or dependencies required' but the provided template loads Chart.js from a CDN, which is an external dependency and requires internet connectivity for first load.
  • Audit risk risky exceeds max_risk=medium
  • Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
  • The term 'stolen' in the metadata and documentation is informal and could be perceived as unprofessional, though it does include proper attribution.

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

76

Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat

Pemeliharaan terbaru

Lulus

100

13 hari sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.