Star200+

Laporan audit skill

adversarial-reviewer Laporan audit.

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

Eksperimental · TinjauPerlu ditinjauDihasilkan 22 Agu 2026Audit metadata heuristik
88
Audit
83
Kepercayaan
91
Kualitas
82
Keamanan
100
Maintain
92
Pasang

Trust Score OpenAgentSkill

83
Shortlist kuat

Trust Score OpenAgentSkill

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

Adopsi GitHub

Lulus

100

25K star GitHub

Aktivitas star/fork

Lulus

97

25K star dan 3.5K fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

100

Diperbarui hari ini

Kejelasan lisensi

Lulus

86

MIT

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Risiko dependensi/runtime

Info

74

network or browser surface, database surface

Ketersediaan pemasangan

Lulus

92

npx skills add alirezarezvani/claude-skills --skill adversarial-reviewer

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Gagal

36

shell or command execution, filesystem or document access

Bukti repositori

Lulus

86

https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/adversarial-reviewer

Status peninjauan

Lulus

88

Data tinjauan AI tersedia

Hasil terbukti Agent

Info

54

Belum ada data hasil Agent

Pemeriksaan

Tinjauan pemasangan dan adopsi

9 Lulus · 6 Perlu ditinjau

Jalur pemasangan

92

Lulus

npx skills add alirezarezvani/claude-skills --skill adversarial-reviewer

Repositori

88

Lulus

https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/adversarial-reviewer

Lisensi

86

Lulus

MIT

Pemeliharaan

100

Lulus

Diperbarui hari ini

Tinjauan AI

88

Lulus

Approved with no listed issues

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

74

Periksa

network or browser surface, database surface

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

36

Perbaiki

shell or command execution, filesystem or document access

Aktivitas star/fork

97

Lulus

25K star dan 3.5K fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

88

Lulus

25K star GitHub

Peringatan

  • Permission surface may require sandboxing
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Permission surface: shell or command execution, filesystem or document access

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.