OpenAgentSkill
GitHub200+

Pre-install eval

faceswap 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
73
Eval report
72
Trust
81
Audit
45
Agent safety

do not auto install

Audit score: Risky

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate faceswap before installing it in an agent workflow
  • research
  • Research agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add calesthio/OpenMontage --skill faceswap

Install command safety

92

pass

standard package or runtime install path

  • npx skills add calesthio/OpenMontage --skill faceswap

Trust score

72

warn

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

  • Strong shortlist
  • 56K GitHub stars
  • AGPL-3.0

Audit score

81

fail

Risky

  • Dependency or permission surface needs review

Agent safety gate

45

fail

This skill should not be selected by an agent without explicit human security review.

  • Do not auto-install. Inspect the source, dependencies, and permission surface first.
  • Audit risk exceeds the requested agent policy

License clarity

86

pass

AGPL-3.0

  • AGPL-3.0

Permission surface

36

fail

secrets or environment access, shell or command execution

  • Shell or command execution: high
  • Network access: medium
  • Secrets or environment access: high

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
  • No explicit limitations section (e.g., file size limits, supported formats, rate limits).
  • Audit risk risky exceeds max_risk=medium
  • High-risk permission hints: Shell or command execution, Secrets or environment access
  • Dependency or permission surface 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

3mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.