Star200+

Evaluasi sebelum pemasangan

pfc-marshall-test 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
70
Laporan evaluasi
68
Kepercayaan
75
Audit
63
Keamanan Agent

Tinjauan manual

Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

94

Lulus

Task wording matches this skill metadata.

  • Evaluate pfc-marshall-test before installing it in an agent workflow
  • Keamanan
  • Security and compliance workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add Echo-aloha/asphalt-codex-skills-5 --skill pfc-marshall-test

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add Echo-aloha/asphalt-codex-skills-5 --skill pfc-marshall-test

Skor kepercayaan

68

Peringatan

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

  • Tinjauan manual
  • 17 star GitHub
  • MIT

Skor audit

75

Peringatan

Perlu ditinjau

  • No executable scripts are included in the skill itself; it depends on external fistPkg and other skills, which limits standalone verification but is not a security risk.

Gerbang keamanan Agent

63

Peringatan

Kandidat yang dapat digunakan, tetapi Agent harus menampilkan catatan izin dan audit sebelum memasang.

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • No executable scripts are included in the skill itself; it depends on external fistPkg and other skills, which limits standalone verification but is not a security risk.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

100

Lulus

Tidak ada cakupan izin berisiko tinggi dalam metadata publik

  • Network 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
  • Low GitHub adoption signal
  • No executable scripts are included in the skill itself; it depends on external fistPkg and other skills, which limits standalone verification but is not a security risk.
  • The SKILL.md excerpt appears truncated in the provided documentation, though the repository likely contains the full file; ensure the complete workflow and limitations are present.
  • References to JTG standards are provided as checklists and explicitly avoid reproducing copyrighted text, which is good, but users must still confirm they have legal copies of the standards.

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

100

2 hari sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.