OpenAgentSkill
GitHub200+

Pre-install eval

better-typography 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
75
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 better-typography before installing it in an agent workflow
  • automation
  • Browser automation workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add jakubkrehel/skills --skill better-typography

Install command safety

92

pass

standard package or runtime install path

  • npx skills add jakubkrehel/skills --skill better-typography

Trust score

74

warn

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

  • Strong shortlist
  • 4.8K GitHub stars
  • MIT

Audit score

81

warn

Needs review

  • SKILL.md is guidance-rich but does not explicitly define an agent workflow with inputs, steps, and output format; adding a 'How to use' section would make it more actionable.

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.
  • SKILL.md is guidance-rich but does not explicitly define an agent workflow with inputs, steps, and output format; adding a 'How to use' section would make it more actionable.

License clarity

86

pass

MIT

  • MIT

Permission surface

72

warn

filesystem or document access, network or browser access

  • Browser automation: medium
  • 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
  • SKILL.md is guidance-rich but does not explicitly define an agent workflow with inputs, steps, and output format; adding a 'How to use' section would make it more actionable.
  • The skill assumes the agent can read the rendered page; when that is not possible, some checks such as widows, wrapping, and truncation are hard to perform from static code alone.
  • Quality score needs review
  • Production credentials, payments, or irreversible account changes without explicit human review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.