Star200+

Evaluasi sebelum pemasangan

Portfolio Health Check 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
84
Laporan evaluasi
76
Kepercayaan
86
Audit
74
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

84

Lulus

Task wording matches this skill metadata.

  • Evaluate Portfolio Health Check before installing it in an agent workflow
  • Finance
  • Finance and quant workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx -y skills add Geeksfino/finskills --skill portfolio-health-check

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx -y skills add Geeksfino/finskills --skill portfolio-health-check

Skor kepercayaan

76

Peringatan

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

  • Shortlist kuat
  • 271 star GitHub
  • Apache-2.0

Skor audit

86

Peringatan

Perlu ditinjau

  • Financial research output is not financial advice; require human review before any live investment decision

Gerbang keamanan Agent

74

Peringatan

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

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • Financial research output is not financial advice; require human review before any live investment decision

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

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
  • Portfolio and suitability conclusions require human review and up-to-date holdings data.
  • No OpenAgentSkill engagement data yet
  • Financial research output is not financial advice; require human review before any live investment decision
  • Financial research output is not financial advice; require human review before any live investment decision.

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

90

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Peringatan

76

6 bulan sejak push

Alternatif tersedia

Info

55

No close alternatives were found in the current shortlist.