OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

Poster 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
73
Kepercayaan
79
Audit
59
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

70

Peringatan

Task fit is weak; compare alternatives before selecting.

  • Evaluate Poster before installing it in an agent workflow
  • Desain dan kreatif
  • Design and creative workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add Player-YN/PawWork_ZhuaZhua --skill Poster

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add Player-YN/PawWork_ZhuaZhua --skill Poster

Skor kepercayaan

73

Peringatan

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

  • Shortlist kuat
  • 1.3K star GitHub
  • MIT

Skor audit

79

Peringatan

Perlu ditinjau

  • The skill relies on platform-specific tools (`run`, `deck`, `acquire`) that are not fully documented in SKILL.md, but this is acceptable for a domain-specific skill.

Gerbang keamanan Agent

59

Peringatan

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

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • The skill relies on platform-specific tools (`run`, `deck`, `acquire`) that are not fully documented in SKILL.md, but this is acceptable for a domain-specific skill.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

72

Peringatan

filesystem or document access, network or browser access

  • Network access: medium
  • Filesystem access: medium
  • Database 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 relies on platform-specific tools (`run`, `deck`, `acquire`) that are not fully documented in SKILL.md, but this is acceptable for a domain-specific skill.
  • Potential risk: `acquire action=image` may fetch external images; ensure it only pulls from trusted sources and validates URLs to avoid malicious content.
  • Quality score needs review
  • Production credentials, payments, or irreversible account changes without explicit human review

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

76

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

Pemeliharaan terbaru

Lulus

88

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.