OpenAgentSkill
GitHub200+

Pre-install eval

cad-mesh-3dgs 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
69
Eval report
71
Trust
76
Audit
56
Agent safety

manual review

Test manually in an isolated workspace and compare against safer alternatives.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate cad-mesh-3dgs before installing it in an agent workflow
  • coding-agents
  • Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add jaccen/Awesome-Gaussian-Skills --skill cad-mesh-3dgs

Install command safety

92

pass

standard package or runtime install path

  • npx skills add jaccen/Awesome-Gaussian-Skills --skill cad-mesh-3dgs

Trust score

71

warn

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

  • Manual review
  • 149 GitHub stars
  • Apache-2.0

Audit score

76

warn

Needs review

  • The SKILL.md excerpt does not include explicit safety or limitation sections, but the skill is purely analytical and does not execute code or access external resources, so no critical risk.

Agent safety gate

56

warn

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The SKILL.md excerpt does not include explicit safety or limitation sections, but the skill is purely analytical and does not execute code or access external resources, so no critical risk.

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

74

warn

filesystem or document access, database access

  • Network access: medium
  • Filesystem access: medium
  • Database 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
  • The SKILL.md excerpt does not include explicit safety or limitation sections, but the skill is purely analytical and does not execute code or access external resources, so no critical risk.
  • No OpenAgentSkill engagement data yet
  • The skill relies on external reference files (methods database, code examples, output templates) which are not fully shown in the excerpt, but they are part of the repository and referenced clearly.
  • Quality score needs review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.