OpenAgentSkill
GitHub200+

Pre-install eval

litert-runtime 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
72
Eval report
77
Trust
79
Audit
59
Agent safety

do not auto install

Install path: No install command or repository handoff is available.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate litert-runtime before installing it in an agent workflow
  • video-creation
  • Multimodal media workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

20

fail

No install command or repository handoff is available.

Install command safety

92

pass

standard package or runtime install path

Trust score

77

warn

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

  • Strong shortlist
  • 459 GitHub stars
  • Apache-2.0

Audit score

79

warn

Needs review

  • Permission surface may require sandboxing

Agent safety gate

59

warn

Usable candidate, but the agent should surface permission and audit notes before installation.

  • The tracked source changed or could not be synchronized. Review the current source before installing.

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

60

warn

filesystem or document access, network or browser 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
  • high-compliance environments without internal security review
  • No major risk signals from current metadata
  • Permission surface may require sandboxing
  • The tracked source changed or could not be synchronized. Review the current source before installing.
  • Financial research output is not financial advice; require human review before any live investment decision

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

2d since push

Alternatives available

pass

82

Alternative skills are available for comparison.