Star200+

Evaluasi sebelum pemasangan

Dolly 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
77
Laporan evaluasi
84
Kepercayaan
76
Audit
60
Keamanan Agent

Tinjauan manual

Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate Dolly before installing it in an agent workflow
  • support-automation
  • Coding agents workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add databrickslabs/dolly

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add databrickslabs/dolly

Skor kepercayaan

84

Lulus

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

  • Shortlist kuat
  • 11K star GitHub
  • Apache-2.0

Skor audit

76

Peringatan

Perlu ditinjau

  • Repository appears stale

Gerbang keamanan Agent

60

Peringatan

Kandidat yang dapat digunakan, tetapi Agent harus menampilkan catatan izin dan audit sebelum memasang.

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • Repository appears stale

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

Cakupan izin

86

Lulus

Akses sistem file atau dokumen

  • 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

  • teams that require actively maintained dependencies
  • production agents without a repository review
  • Repository looks stale
  • Repository appears stale
  • Financial research output is not financial advice; require human review before any live investment decision
  • Financial research output is not financial advice; require human review before any live investment decision.

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

90

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Gagal

22

3 tahun sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.