Star0

Pre-install eval

shadcnblocks skill 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
70
Eval
72
Trust
78
Audit
54
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 shadcnblocks skill before installing it in an agent workflow
  • design-creative
  • GitHub automation workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add masonjames/shadcnblocks-skill

Install command safety

92

pass

standard package or runtime install path

  • npx skills add masonjames/shadcnblocks-skill

Trust score

72

warn

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

  • Strong shortlist
  • 17 GitHub stars
  • MIT

Audit score

78

warn

Needs review

  • Manual curator approval: useful shadcn UI workflow. Adoption signal is still low; review generated UI and dependencies.

Agent safety gate

54

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

76

warn

shell or command execution

  • Shell or command execution: high
  • Network 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
  • Low GitHub adoption signal
  • Manual curator approval: useful shadcn UI workflow. Adoption signal is still low; review generated UI and dependencies.
  • No OpenAgentSkill engagement data yet
  • High-risk permission hints: Shell or command execution

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

94

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

Pushed today

Alternatives available

pass

82

Alternative skills are available for comparison.