Laporan audit skill
Agency Agents Zh Laporan audit.
🎭 211 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 16 种工具，覆盖工程/设计/营销/金融等 18 个部门。含 46 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）
Trust Score OpenAgentSkill
Trust Score OpenAgentSkill
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
Adopsi GitHub
Lulus100
15K star GitHub
Aktivitas star/fork
Lulus97
15K star dan 2.6K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
2 bulan sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Lulus90
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Info72
Cakupan eksekusi perintah
Ketersediaan pemasangan
Lulus92
npx skills add jnMetaCode/agency-agents-zh
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Info62
shell or command execution, filesystem or document access
Bukti repositori
Lulus86
https://github.com/jnMetaCode/agency-agents-zh
Status peninjauan
Lulus88
Data tinjauan AI tersedia
Hasil terbukti Agent
Info54
Belum ada data hasil Agent
Pemeriksaan
Tinjauan pemasangan dan adopsi
Jalur pemasangan
92
npx skills add jnMetaCode/agency-agents-zh
Repositori
88
https://github.com/jnMetaCode/agency-agents-zh
Lisensi
86
MIT
Pemeliharaan
88
2 bulan sejak push
Tinjauan AI
88
Approved with no listed issues
Kelengkapan README/SKILL.md
90
Usable description available
Risiko dependensi
72
Cakupan eksekusi perintah
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
62
shell or command execution, filesystem or document access
Aktivitas star/fork
97
15K star dan 2.6K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
15K star GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Peringatan
- 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.
Metode
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Bandingkan opsi sekitar