Laporan audit skill
hive.context-preservation Laporan audit.
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
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
11K star GitHub
Aktivitas star/fork
Lulus100
11K star dan 5.7K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
2 bulan sejak push
Kejelasan lisensi
Lulus86
Apache-2.0
Kelengkapan README/SKILL.md
Lulus86
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Lulus82
network or browser surface
Ketersediaan pemasangan
Lulus92
npx skills add aden-hive/hive --skill hive.context-preservation
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Info74
network or browser access, database access
Bukti repositori
Lulus86
https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/context-preservation
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 aden-hive/hive --skill hive.context-preservation
Repositori
88
https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/context-preservation
Lisensi
86
Apache-2.0
Pemeliharaan
88
2 bulan sejak push
Tinjauan AI
88
Approved with no listed issues
Kelengkapan README/SKILL.md
86
Usable description available
Risiko dependensi
82
network or browser surface
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
74
network or browser access, database access
Aktivitas star/fork
100
11K star dan 5.7K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
11K star GitHub
Peringatan
- Quality score needs review
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