Star200+

Pre-install eval

Agent Skills 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
77
Eval report
78
Trust
84
Audit
60
Agent safety

do not auto install

Audit score: Risky

Required gates

Checks an agent must pass before install

Open JSON

Task fit

94

pass

Task wording matches this skill metadata.

  • Evaluate Agent Skills before installing it in an agent workflow
  • coding-agents
  • GitHub automation workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add mblode/agent-skills

Install command safety

92

pass

standard package or runtime install path

  • npx skills add mblode/agent-skills

Trust score

78

warn

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

  • Strong shortlist
  • 75 GitHub stars
  • MIT

Audit score

84

fail

Risky

  • Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required

Agent safety gate

60

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

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
  • high-compliance environments without internal security review
  • No OpenAgentSkill engagement data yet
  • Audit risk risky exceeds max_risk=medium
  • High-risk permission hints: Shell or command execution
  • Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

100

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

3d since push

Alternatives available

pass

82

Alternative skills are available for comparison.