OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

evals-clarify 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
72
Laporan evaluasi
73
Kepercayaan
77
Audit
65
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 evals-clarify before installing it in an agent workflow
  • automation
  • Browser automation workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add tikalk/adlc-team-skills --skill evals-clarify

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add tikalk/adlc-team-skills --skill evals-clarify

Skor kepercayaan

73

Peringatan

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

  • Shortlist kuat
  • 132 star GitHub
  • MIT

Skor audit

77

Peringatan

Perlu ditinjau

  • SKILL.md excerpt appears truncated at the end, but the provided content is complete enough for evaluation.

Gerbang keamanan Agent

65

Peringatan

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

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • SKILL.md excerpt appears truncated at the end, but the provided content is complete enough for evaluation.

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
  • SKILL.md excerpt appears truncated at the end, but the provided content is complete enough for evaluation.
  • The bash script is minimal and only outputs environment info; it does not perform the core skill logic, but that is acceptable as a setup helper.
  • Quality score needs review
  • Stars/forks activity: 132 stars, 1 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.