OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

paper-details 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.

Perlu ditinjauRisiko sedangTinjau Kebijakan
69
Laporan evaluasi
72
Kepercayaan
76
Audit
56
Keamanan Agent

Tinjauan manual

Test manually in an isolated workspace and compare against safer alternatives.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate paper-details before installing it in an agent workflow
  • Riset
  • Content automation workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add mathbullet/skills --skill paper-details

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add mathbullet/skills --skill paper-details

Skor kepercayaan

72

Peringatan

Good trust signals with a few areas worth checking before rollout.

  • Shortlist kuat
  • 119 star GitHub
  • MIT

Skor audit

76

Peringatan

Perlu ditinjau

  • The skill depends on external skills (documenting-with-sources and writing-quotation) which are not included in this submission; ensure they are available in the agent environment.

Gerbang keamanan Agent

56

Peringatan

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The skill depends on external skills (documenting-with-sources and writing-quotation) which are not included in this submission; ensure they are available in the agent environment.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

86

Lulus

Akses sistem file atau dokumen

  • Browser automation: medium
  • 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 depends on external skills (documenting-with-sources and writing-quotation) which are not included in this submission; ensure they are available in the agent environment.
  • The script uses `uv run`, which requires the `uv` tool to be installed; this is not mentioned in SKILL.md.
  • Quality score needs review
  • Stars/forks activity: 119 stars, 3 forks; issue activity unavailable in current metadata

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Lulus

88

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.