Star200+

Evaluasi sebelum pemasangan

Directus 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
83
Laporan evaluasi
86
Kepercayaan
89
Audit
57
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 Directus before installing it in an agent workflow
  • data-analysis
  • Coding agents workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add directus/directus

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add directus/directus

Skor kepercayaan

86

Lulus

Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.

  • Kandidat produksi
  • 36K star GitHub
  • Tidak diketahui

Skor audit

89

Peringatan

Perlu ditinjau

  • Lisensi tidak jelas

Gerbang keamanan Agent

57

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

42

Peringatan

Tidak diketahui

  • Tidak diketahui

Cakupan izin

60

Peringatan

filesystem or document access, network or browser access

  • Network access: medium
  • Filesystem 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
  • Lingkungan berkompliansi tinggi tanpa tinjauan keamanan internal
  • No major risk signals from current metadata
  • Petunjuk izin berisiko tinggi: Secrets or environment access
  • Lisensi tidak jelas
  • Permission surface may require sandboxing

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

90

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Lulus

88

2 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.