OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

archive 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
70
Laporan evaluasi
71
Kepercayaan
78
Audit
46
Keamanan Agent

do not auto install

Permission surface: secrets or environment access, filesystem or document access

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate archive before installing it in an agent workflow
  • Riset
  • RAG and knowledge workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add ReScienceLab/opc-skills --skill archive

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add ReScienceLab/opc-skills --skill archive

Skor kepercayaan

71

Peringatan

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

  • Tinjauan manual
  • 1.8K star GitHub
  • Apache-2.0

Skor audit

78

Peringatan

Perlu ditinjau

  • Permission surface may require sandboxing

Gerbang keamanan Agent

46

Peringatan

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • Petunjuk izin berisiko tinggi: Secrets or environment access

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

Cakupan izin

48

Gagal

secrets or environment access, filesystem or document access

  • Network access: medium
  • Filesystem access: medium
  • Secrets or environment access: high

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 SessionStart hook loads .archive/MEMORY.md into the model context without sanitization or explicit untrusted-data boundaries. Archived content from previous sessions could contain prompt-injection-like instructions or sensitive material.
  • Petunjuk izin berisiko tinggi: Secrets or environment access
  • Permission surface may require sandboxing
  • The skill instructs that .archive/ must be in .gitignore, but it does not verify or enforce this, so sensitive local notes could accidentally be committed.

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

76

Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat

Pemeliharaan terbaru

Lulus

88

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.