OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

absolute-work 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.

GagalRisiko tinggiBlokir Kebijakan
60
Laporan evaluasi
63
Kepercayaan
70
Audit
26
Keamanan Agent

do not auto install

Audit score: Risky

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

94

Lulus

Task wording matches this skill metadata.

  • Evaluate absolute-work before installing it in an agent workflow
  • workflow
  • Workflow automation workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add maddhruv/absolute --skill absolute-work

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add maddhruv/absolute --skill absolute-work

Skor kepercayaan

63

Peringatan

Potentially useful, but at least one trust signal needs human inspection.

  • Tinjauan manual
  • 211 star GitHub
  • MIT

Skor audit

70

Gagal

Berisiko

  • Dependency or permission surface needs review

Gerbang keamanan Agent

26

Gagal

This skill should not be selected by an agent without explicit human security review.

  • Do not auto-install. Inspect the source, dependencies, and permission surface first.
  • Audit risk exceeds the requested agent policy

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

24

Gagal

secrets or environment access, shell or command execution

  • Shell or command execution: high
  • 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.md is very long and dense; some users may find it overwhelming, but the structure is clear.
  • Audit risk risky exceeds max_risk=medium
  • Petunjuk izin berisiko tinggi: Shell or command execution, Secrets or environment access
  • Dependency or permission surface needs 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

Peringatan

76

3 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.