OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

master-ouyi 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
69
Kepercayaan
76
Audit
60
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 master-ouyi before installing it in an agent workflow
  • Desain dan kreatif
  • Design and creative workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add xr843/Master-skill --skill master-ouyi

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add xr843/Master-skill --skill master-ouyi

Skor kepercayaan

69

Peringatan

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

  • Tinjauan manual
  • 382 star GitHub
  • MIT

Skor audit

76

Peringatan

Perlu ditinjau

  • SKILL.md frontmatter sources omit 《灵峰宗论》(J36nB348) and 《成唯识论观心法要》, while references/teaching.md and meta.json cite them; this creates a citation-contract inconsistency that could lead to unauthorized source usage.

Gerbang keamanan Agent

60

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 frontmatter sources omit 《灵峰宗论》(J36nB348) and 《成唯识论观心法要》, while references/teaching.md and meta.json cite them; this creates a citation-contract inconsistency that could lead to unauthorized source usage.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

86

Lulus

network or browser access

  • Network 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
  • SKILL.md frontmatter sources omit 《灵峰宗论》(J36nB348) and 《成唯识论观心法要》, while references/teaching.md and meta.json cite them; this creates a citation-contract inconsistency that could lead to unauthorized source usage.
  • Version metadata is inconsistent: SKILL.md says 0.5.0 while meta.json says 1.0.0.
  • Some excerpts in references/teaching.md appear to be synthesized teaching summaries rather than verbatim canonical quotations, which can blur the boundary between original text and commentary.
  • Quality score needs 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.