Star200+

Pre-install eval

RNSkill Local Talking-Head Cut 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
79
Eval
73
Trust
83
Audit
67
Safety

do not auto install

License clarity: CC-BY-NC-4.0 (repository; verify skill-level terms)

Required gates

Checks an agent must pass before install

Open JSON

Task fit

94

pass

Task wording matches this skill metadata.

  • Evaluate RNSkill Local Talking-Head Cut before installing it in an agent workflow
  • Video Creation
  • Coding agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx -y skills add Pluviobyte/rnskill --skill ra-local-talking-head-cut

Install command safety

92

pass

standard package or runtime install path

  • npx -y skills add Pluviobyte/rnskill --skill ra-local-talking-head-cut

Trust score

73

warn

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

  • Strong shortlist
  • 823 GitHub stars
  • CC-BY-NC-4.0 (repository; verify skill-level terms)

Audit score

83

warn

Needs review

  • License restricts commercial reuse

Agent safety gate

67

warn

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

  • Require human approval before installing into a real workspace.
  • License restricts commercial reuse

License clarity

58

fail

CC-BY-NC-4.0 (repository; verify skill-level terms)

  • CC-BY-NC-4.0 (repository; verify skill-level terms)

Permission surface

86

pass

filesystem or document access

  • 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
  • production agents without a repository review
  • May require external ASR credentials and upload access for source media.
  • No OpenAgentSkill engagement data yet
  • License restricts commercial reuse
  • Human approval is required before semantic edits, deletion, or rendering.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

90

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

1d since push

Alternatives available

pass

82

Alternative skills are available for comparison.