Star0

Pre-install eval

JSONBench 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
65
Eval
69
Trust
72
Audit
40
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

94

pass

Task wording matches this skill metadata.

  • Evaluate JSONBench before installing it in an agent workflow
  • data-analysis
  • RAG and knowledge workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add ClickHouse/JSONBench

Install command safety

92

pass

standard package or runtime install path

  • npx skills add ClickHouse/JSONBench

Trust score

69

warn

Potentially useful, but at least one trust signal needs human inspection.

  • Manual review
  • 178 GitHub stars
  • Unknown

Audit score

72

warn

Needs review

  • License is unclear

Agent safety gate

40

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

42

warn

Unknown

  • Unknown

Permission surface

50

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 OpenAgentSkill engagement data yet
  • High-risk permission hints: Shell or command execution
  • License is unclear
  • Permission surface may require sandboxing

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

74

Public metadata needs stronger README/SKILL.md context

Recent maintenance

warn

76

4mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.