OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

explore-ml-data 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
69
Laporan evaluasi
74
Kepercayaan
76
Audit
48
Keamanan Agent

do not auto install

Install path: No install command or repository handoff is available.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

94

Lulus

Task wording matches this skill metadata.

  • Evaluate explore-ml-data before installing it in an agent workflow
  • Keamanan
  • Security and compliance workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

20

Gagal

No install command or repository handoff is available.

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Skor kepercayaan

74

Peringatan

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

  • Shortlist kuat
  • 119 star GitHub
  • BSD-3-Clause

Skor audit

76

Peringatan

Perlu ditinjau

  • Permission surface may require sandboxing

Gerbang keamanan Agent

48

Peringatan

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

  • The tracked source changed or could not be synchronized. Review the current source before installing.

Kejelasan lisensi

86

Lulus

BSD-3-Clause

  • BSD-3-Clause

Cakupan izin

46

Gagal

secrets or environment access, filesystem or document access

  • Network access: medium
  • Filesystem access: medium
  • Secrets or environment access: high

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
  • Lingkungan berkompliansi tinggi tanpa tinjauan keamanan internal
  • No major risk signals from current metadata
  • Petunjuk izin berisiko tinggi: Secrets or environment access
  • Permission surface may require sandboxing
  • The tracked source changed or could not be synchronized. Review the current source before installing.

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Lulus

88

2 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.