OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

ads 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
79
Laporan evaluasi
77
Kepercayaan
85
Audit
61
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 ads before installing it in an agent workflow
  • Desain dan kreatif
  • Design and creative workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add coreyhaines31/marketingskills --skill ads

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add coreyhaines31/marketingskills --skill ads

Skor kepercayaan

77

Peringatan

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

  • Shortlist kuat
  • 47K star GitHub
  • MIT

Skor audit

85

Lulus

Aman untuk dicoba

  • The skill description states the agent has 'direct access to ad platform accounts,' but SKILL.md does not define credential-handling, permission boundaries, or a hard budget-confirmation gate before taking actions on live accounts.

Gerbang keamanan Agent

61

Peringatan

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

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • The skill description states the agent has 'direct access to ad platform accounts,' but SKILL.md does not define credential-handling, permission boundaries, or a hard budget-confirmation gate before taking actions on live accounts.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

74

Peringatan

filesystem or document access, database access

  • Browser automation: medium
  • 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
  • The skill description states the agent has 'direct access to ad platform accounts,' but SKILL.md does not define credential-handling, permission boundaries, or a hard budget-confirmation gate before taking actions on live accounts.
  • The excerpt is incomplete after the 'Before Starting' and 'Reference Routing' sections, so full verification of all referenced playbooks was not possible from the provided material.
  • The SKILL.md metadata contains only a version and no explicit scope/limitations section, which could lead to overuse on tasks outside the skill's core expertise.
  • Production credentials, payments, or irreversible account changes without explicit human 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.