OpenAgentSkill
GitHub200+

Pre-install eval

expo 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 report
69
Trust
76
Audit
60
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 expo before installing it in an agent workflow
  • design-creative
  • Design and creative workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add pproenca/dot-skills --skill expo

Install command safety

92

pass

standard package or runtime install path

  • npx skills add pproenca/dot-skills --skill expo

Trust score

69

warn

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

  • Manual review
  • 202 GitHub stars
  • MIT

Audit score

76

warn

Needs review

  • Inconsistent rule counts: SKILL.md and metadata.json state 54 rules, while AGENTS.md and README.md state 42 rules. This discrepancy could confuse agents.

Agent safety gate

60

warn

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

  • Require human approval before installing into a real workspace.
  • Inconsistent rule counts: SKILL.md and metadata.json state 54 rules, while AGENTS.md and README.md state 42 rules. This discrepancy could confuse agents.

License clarity

86

pass

MIT

  • MIT

Permission surface

72

warn

filesystem or document access, network or browser 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
  • Inconsistent rule counts: SKILL.md and metadata.json state 54 rules, while AGENTS.md and README.md state 42 rules. This discrepancy could confuse agents.
  • No OpenAgentSkill engagement data yet
  • SKILL.md excerpt is truncated in the provided documentation, but the full file may be complete; ensure it includes all rule references and is not accidentally cut off.
  • The skill lacks an explicit 'Limitations' or 'When Not to Use' section in SKILL.md, which would help agents understand boundaries.

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

info

55

No close alternatives were found in the current shortlist.