OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

github-repo 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.

Perlu ditinjauRisiko sedangTinjau Kebijakan
63
Laporan evaluasi
66
Kepercayaan
71
Audit
39
Keamanan Agent

Tinjauan manual

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

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

94

Lulus

Task wording matches this skill metadata.

  • Evaluate github-repo before installing it in an agent workflow
  • Keamanan
  • GitHub automation workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add jdevalk/skills --skill github-repo

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add jdevalk/skills --skill github-repo

Skor kepercayaan

66

Peringatan

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

  • Tinjauan manual
  • 97 star GitHub
  • MIT

Skor audit

71

Peringatan

Perlu ditinjau

  • No explicit statement about not accessing or exfiltrating secrets, but the skill operates on user-provided repos and does not appear to request sensitive data.

Gerbang keamanan Agent

39

Peringatan

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

62

Peringatan

shell or command execution, filesystem or document access

  • Shell or command execution: high
  • Browser automation: medium
  • Network 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
  • No explicit statement about not accessing or exfiltrating secrets, but the skill operates on user-provided repos and does not appear to request sensitive data.
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
  • The skill may overwrite files, but it explicitly instructs to ask before overwriting, which mitigates risk.
  • Quality score needs review

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Peringatan

76

3 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.