OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

manuscript-manager 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
69
Laporan evaluasi
70
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 manuscript-manager 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 felipelobomotta-blip/book-genesis-studio --skill manuscript-manager

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add felipelobomotta-blip/book-genesis-studio --skill manuscript-manager

Skor kepercayaan

70

Peringatan

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

  • Tinjauan manual
  • 115 star GitHub
  • MIT

Skor audit

76

Peringatan

Perlu ditinjau

  • SKILL.md does not explicitly instruct the agent to treat PROJECT_STATE.yaml and other project files as untrusted data, leaving room for prompt injection if a state file contains instructions.

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 does not explicitly instruct the agent to treat PROJECT_STATE.yaml and other project files as untrusted data, leaving room for prompt injection if a state file contains instructions.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

100

Lulus

Tidak ada cakupan izin berisiko tinggi dalam metadata publik

  • 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 does not explicitly instruct the agent to treat PROJECT_STATE.yaml and other project files as untrusted data, leaving room for prompt injection if a state file contains instructions.
  • Safe operating boundaries are not fully explicit: the skill mentions creating missing folders and updating PROJECT_STATE.yaml, but does not clearly prohibit destructive actions like deleting or rewriting chapter files.
  • The consistency check for word count and chapter status is underspecified; different agents may count words or infer status differently.
  • 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.