Evaluasi sebelum pemasangan
Anthropic Brand Guidelines 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.
Tinjauan manual
Tinjau halaman audit, lalu izinkan pemasangan Agent dalam alur kerja sandbox.
Gerbang wajib
Pemeriksaan yang harus dilalui Agent sebelum memasang
Kecocokan tugas
84
Task wording matches this skill metadata.
- Evaluate Anthropic Brand Guidelines 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
Install handoff is available.
- npx skills add anthropics/skills --skill brand-guidelines
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
- npx skills add anthropics/skills --skill brand-guidelines
Skor kepercayaan
91
Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.
- Kandidat produksi
- 171K star GitHub
- Source terms (see LICENSE.txt)
Skor audit
93
Aman untuk dicoba
- Brand guidance is source-specific; do not apply Anthropic identity to unrelated organizations without permission.
Gerbang keamanan Agent
81
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
Source terms (see LICENSE.txt)
- Source terms (see LICENSE.txt)
Cakupan izin
100
Tidak ada cakupan izin berisiko tinggi dalam metadata publik
- Network access: medium
Rencana validasi
Langkah Agent berikutnya
- 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
- 2Install in an isolated workspace or sandbox with no production secrets available.
- 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
- 4Compare the selected skill against at least one alternative when the eval status is review or failed.
- 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
- Brand guidance is source-specific; do not apply Anthropic identity to unrelated organizations without permission.
- Production credentials, payments, or irreversible account changes without explicit human review
- Sensitive private data before reviewing repository code, license, and permission surface
Pemeriksaan pendukung
Sinyal kepercayaan di balik keputusan
Kelengkapan README/SKILL.md
Lulus90
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Pemeliharaan terbaru
Lulus100
1 hari sejak push
Alternatif tersedia
Lulus82
Alternative skills are available for comparison.