OpenAgentSkill
GitHub200+

Pre-install eval

nemo-curator 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.

FailedHigh riskBLOCK Policy
77
Eval report
81
Trust
85
Audit
57
Agent safety

do not auto install

Permission surface: shell or command execution, filesystem or document access

Required gates

Checks an agent must pass before install

Open JSON

Task fit

70

warn

Task fit is weak; compare alternatives before selecting.

  • Evaluate nemo-curator before installing it in an agent workflow
  • video-creation
  • Multimodal media workflows; OpenAI Agents teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add Orchestra-Research/AI-Research-SKILLs --skill nemo-curator

Install command safety

92

pass

standard package or runtime install path

  • npx skills add Orchestra-Research/AI-Research-SKILLs --skill nemo-curator

Trust score

81

warn

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

  • Strong shortlist
  • 13K GitHub stars
  • MIT

Audit score

85

warn

Needs review

  • Dependency or permission surface needs review

Agent safety gate

57

warn

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • High-risk permission hints: Shell or command execution

License clarity

86

pass

MIT

  • MIT

Permission surface

48

fail

shell or command execution, filesystem or document access

  • Shell or command execution: high
  • Network access: medium
  • Filesystem 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
  • high-compliance environments without internal security review
  • No major risk signals from current metadata
  • High-risk permission hints: Shell or command execution
  • Dependency or permission surface needs review
  • Permission surface may require sandboxing

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

94

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

1d since push

Alternatives available

pass

82

Alternative skills are available for comparison.