OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

calc-sample-size 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
68
Laporan evaluasi
71
Kepercayaan
76
Audit
48
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 calc-sample-size before installing it in an agent workflow
  • Riset
  • Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add Aperivue/medsci-skills --skill calc-sample-size

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add Aperivue/medsci-skills --skill calc-sample-size

Skor kepercayaan

71

Peringatan

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

  • Tinjauan manual
  • 291 star GitHub
  • MIT

Skor audit

76

Peringatan

Perlu ditinjau

  • The skill uses Bash, which could be risky if the model executes arbitrary user-provided commands. The SKILL.md excerpt does not explicitly state that only generated code should be run.

Gerbang keamanan Agent

48

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: eksekusi shell atau perintah

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

76

Peringatan

Eksekusi shell atau perintah

  • 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 uses Bash, which could be risky if the model executes arbitrary user-provided commands. The SKILL.md excerpt does not explicitly state that only generated code should be run.
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
  • The SKILL.md is truncated in the excerpt, but the visible content is thorough and well-organized.
  • Quality score 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

Lulus

88

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.