OpenAgentSkill
GitHub200+

Pre-install eval

deck-obsidian-claude Eval report.

A machine-readable install decision for agents: task fit, Trust Score, Audit Score, install safety, permission surface, and a concrete validation plan before this skill touches a workspace.

Needs reviewMedium riskREVIEW Policy
82
Eval report
80
Trust
85
Audit
73
Agent safety

manual review

Review the audit page, then allow agent install in a sandboxed workflow.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate deck-obsidian-claude before installing it in an agent workflow
  • slides
  • Presentation generation workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add nexu-io/html-anything --skill deck-obsidian-claude

Install command safety

92

pass

standard package or runtime install path

  • npx skills add nexu-io/html-anything --skill deck-obsidian-claude

Trust score

80

warn

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

  • Strong shortlist
  • 8.6K GitHub stars
  • Apache-2.0

Audit score

85

pass

Safe to try

  • SKILL.md 缺少明确的输入、输出、工作流程和限制说明，仅提供了布局描述。

Agent safety gate

73

warn

Good audit and safety signals with no high-risk permission hints in public metadata.

  • Review the audit page, then allow agent install in a sandboxed workflow.
  • Safe-to-try audit

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

100

pass

no high-risk permission surface in public metadata

  • Network access: medium

Validation plan

What the agent should do next

  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.

Do not use when

Conditions that require another skill

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • SKILL.md 缺少明确的输入、输出、工作流程和限制说明，仅提供了布局描述。
  • Quality score needs review
  • Production credentials, payments, or irreversible account changes without explicit human review
  • Sensitive private data before reviewing repository code, license, and permission surface

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

68

Public metadata needs stronger README/SKILL.md context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.