OpenAgentSkill
GitHub200+

Pre-install eval

database-optimizer 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
76
Eval report
74
Trust
81
Audit
61
Agent safety

manual review

Require human approval before installing into a real workspace.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate database-optimizer before installing it in an agent workflow
  • design-creative
  • Database and SQL workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add Jeffallan/claude-skills --skill database-optimizer

Install command safety

92

pass

standard package or runtime install path

  • npx skills add Jeffallan/claude-skills --skill database-optimizer

Trust score

74

warn

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

  • Strong shortlist
  • 11K GitHub stars
  • MIT

Audit score

81

warn

Needs review

  • Permission surface may require sandboxing

Agent safety gate

61

warn

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

  • Require human approval before installing into a real workspace.
  • Permission surface may require sandboxing

License clarity

86

pass

MIT

  • MIT

Permission surface

60

warn

filesystem or document access, network or browser access

  • Network access: medium
  • Filesystem access: medium
  • Database 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
  • The skill includes commands that modify database configuration globally (ALTER SYSTEM, SET GLOBAL) without an explicit mandatory human-approval gate before production changes.
  • Permission surface may require sandboxing
  • No explicit guidance on handling database credentials, connection safety, or least-privilege access.
  • Rollback instructions are general rather than concrete per operation, which could be risky when applying configuration changes.

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.