OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

code-quality 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
66
Laporan evaluasi
70
Kepercayaan
74
Audit
54
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 code-quality 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 motlin/claude-code-plugins --skill code-quality

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add motlin/claude-code-plugins --skill code-quality

Skor kepercayaan

70

Peringatan

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

  • Tinjauan manual
  • 20 star GitHub
  • Apache-2.0

Skor audit

74

Peringatan

Perlu ditinjau

  • Low GitHub adoption signal

Gerbang keamanan Agent

54

Peringatan

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • Low GitHub adoption signal

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

Cakupan izin

74

Peringatan

filesystem or document access, database access

  • Network access: medium
  • Filesystem access: medium
  • Database 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
  • Low GitHub adoption signal
  • No OpenAgentSkill engagement data yet
  • Persetujuan tinjauan AI belum ada
  • Quality score needs review

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

60

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

Pemeliharaan terbaru

Lulus

100

Diperbarui hari ini

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.