OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

cs-recover-skill 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
71
Laporan evaluasi
71
Kepercayaan
76
Audit
64
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 cs-recover-skill 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 ChenShuo2004/cs-skills --skill cs-recover-skill

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add ChenShuo2004/cs-skills --skill cs-recover-skill

Skor kepercayaan

71

Peringatan

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

  • Tinjauan manual
  • 116 star GitHub
  • MIT

Skor audit

76

Peringatan

Perlu ditinjau

  • Documentation is Chinese-only, which may reduce usability for non-Chinese-speaking agents or reviewers.

Gerbang keamanan Agent

64

Peringatan

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

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • Documentation is Chinese-only, which may reduce usability for non-Chinese-speaking agents or reviewers.

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
  • Documentation is Chinese-only, which may reduce usability for non-Chinese-speaking agents or reviewers.
  • No OpenAgentSkill engagement data yet
  • The skill repeatedly references GPT-5.6 specifically, which may be confusing if the skill is used with other models or in a model-agnostic agent framework.
  • Quality score needs review

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

60

Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat

Pemeliharaan terbaru

Lulus

88

2 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.