OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

Token Profile 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
63
Laporan evaluasi
70
Kepercayaan
67
Audit
39
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 Token Profile before installing it in an agent workflow
  • web3-analytics
  • Coding agents workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

20

Gagal

No install command or repository handoff is available.

Keamanan perintah pemasangan

68

Peringatan

credential-bearing install command, standard package or runtime install path

Skor kepercayaan

70

Peringatan

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

  • Tinjauan manual
  • 911 star GitHub
  • MIT

Skor audit

67

Gagal

Berisiko

  • Permission surface may require sandboxing

Gerbang keamanan Agent

39

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

60

Peringatan

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

  • teams that require actively maintained dependencies
  • production agents without a repository review
  • Repository looks stale
  • Audit risk risky exceeds max_risk=medium
  • Petunjuk izin berisiko tinggi: Secrets or environment access
  • Permission surface may require sandboxing

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

74

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

Pemeliharaan terbaru

Gagal

38

1 tahun sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.