OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

autofix 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
65
Laporan evaluasi
65
Kepercayaan
73
Audit
49
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

84

Lulus

Task wording matches this skill metadata.

  • Evaluate autofix before installing it in an agent workflow
  • Agent pemrograman
  • Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add devbrother2024/skills --skill autofix

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add devbrother2024/skills --skill autofix

Skor kepercayaan

65

Peringatan

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

  • Tinjauan manual
  • 91 star GitHub
  • MIT

Skor audit

73

Peringatan

Perlu ditinjau

  • Permission surface may require sandboxing

Gerbang keamanan Agent

49

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: Secrets or environment access

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

60

Peringatan

secrets or environment access, network or browser access

  • Network 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
  • production agents without a repository review
  • The SKILL.md is written in Korean, which may limit accessibility for non-Korean users, but this is not a functional issue.
  • Petunjuk izin berisiko tinggi: Secrets or environment access
  • Permission surface may require sandboxing
  • The security rules section is referenced but not fully included in the excerpt; ensure it is present in the full SKILL.md.

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

88

2 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.