OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

ima-dai-sdk 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
81
Laporan evaluasi
79
Kepercayaan
85
Audit
73
Keamanan Agent

Tinjauan manual

Tinjau halaman audit, lalu izinkan pemasangan Agent dalam alur kerja sandbox.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate ima-dai-sdk before installing it in an agent workflow
  • automation
  • Multimodal media workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add google/skills --skill ima-dai-sdk

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add google/skills --skill ima-dai-sdk

Skor kepercayaan

79

Peringatan

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

  • Shortlist kuat
  • 19K star GitHub
  • Apache-2.0

Skor audit

85

Lulus

Aman untuk dicoba

  • Parsed SKILL.md metadata shows description as '>-' and no tags or frameworks, which may indicate frontmatter YAML is not being parsed cleanly by the evaluator.

Gerbang keamanan Agent

73

Peringatan

Sinyal audit dan keamanan baik tanpa petunjuk izin berisiko tinggi dalam metadata publik.

  • Tinjau halaman audit, lalu izinkan pemasangan Agent dalam alur kerja sandbox.
  • Audit aman untuk dicoba

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

Cakupan izin

100

Lulus

Tidak ada cakupan izin berisiko tinggi dalam metadata publik

  • 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
  • Parsed SKILL.md metadata shows description as '>-' and no tags or frameworks, which may indicate frontmatter YAML is not being parsed cleanly by the evaluator.
  • Some reference guide contents are truncated in the submission excerpt, so full verification of all code snippets is limited.
  • Quality score needs review
  • Production credentials, payments, or irreversible account changes without explicit human review

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

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.