OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

sglang-xpu-bench 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
55
Laporan evaluasi
58
Kepercayaan
67
Audit
23
Keamanan Agent

do not auto install

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

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate sglang-xpu-bench before installing it in an agent workflow
  • automation
  • Browser automation workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add intel/gpu-ai-skills --skill sglang-xpu-bench

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add intel/gpu-ai-skills --skill sglang-xpu-bench

Skor kepercayaan

58

Gagal

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

  • Tinjauan manual
  • 22 star GitHub
  • Apache-2.0

Skor audit

67

Peringatan

Perlu ditinjau

  • Dependency or permission surface needs review

Gerbang keamanan Agent

23

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.
  • Metadata combines secrets access with shell or command execution

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

Cakupan izin

22

Gagal

secrets or environment access, shell or command execution

  • 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
  • Low GitHub adoption signal
  • The skill uses `docker exec -it` which may require a TTY; in non-interactive agent environments, this could cause failures. Consider using `docker exec -i` or documenting the need for a pseudo-TTY.
  • Petunjuk izin berisiko tinggi: Shell or command execution, Secrets or environment access
  • Dependency or permission surface 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.