OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

code-stats 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
68
Laporan evaluasi
72
Kepercayaan
78
Audit
50
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

70

Peringatan

Task fit is weak; compare alternatives before selecting.

  • Evaluate code-stats before installing it in an agent workflow
  • Keamanan
  • Security and compliance workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add alibaba/skill-up --skill code-stats

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add alibaba/skill-up --skill code-stats

Skor kepercayaan

72

Peringatan

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

  • Shortlist kuat
  • 846 star GitHub
  • Apache-2.0

Skor audit

78

Peringatan

Perlu ditinjau

  • SKILL.md excerpt appears truncated at 'Sort b' but the full file likely continues; no functional impact.

Gerbang keamanan Agent

50

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

Apache-2.0

  • Apache-2.0

Cakupan izin

62

Peringatan

shell or command execution, filesystem or document access

  • Shell or command execution: high
  • Network access: medium
  • Filesystem 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
  • SKILL.md excerpt appears truncated at 'Sort b' but the full file likely continues; no functional impact.
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
  • No explicit handling for binary files or hidden directories (e.g., .git) which could skew statistics.
  • 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

Lulus

88

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.