OpenAgentSkill
GitHub200+

Pre-install eval

check-accessibility 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
72
Trust
81
Audit
65
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 check-accessibility before installing it in an agent workflow
  • design-creative
  • Design and creative workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add AgnosticUI/agnosticui --skill check-accessibility

Install command safety

92

pass

standard package or runtime install path

  • npx skills add AgnosticUI/agnosticui --skill check-accessibility

Trust score

72

warn

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

  • Strong shortlist
  • 828 GitHub stars
  • Apache-2.0

Audit score

81

warn

Needs review

  • SKILL.md does not warn that content fetched from the web via WebSearch/WebFetch is untrusted and must not override the skill's instructions or repository policies.

Agent safety gate

65

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 does not warn that content fetched from the web via WebSearch/WebFetch is untrusted and must not override the skill's instructions or repository policies.

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

86

pass

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
  • SKILL.md does not warn that content fetched from the web via WebSearch/WebFetch is untrusted and must not override the skill's instructions or repository policies.
  • The workflow depends on `.claude/PROJECT_CONTEXT.md` but does not describe fallback behavior if that file is missing or incomplete.
  • The skill is primarily a static code-review workflow; it does not clarify that runtime accessibility behavior, such as actual keyboard interaction or screen reader output, cannot be fully verified without additional tooling or browser testing.
  • Quality score needs review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

70

Public metadata needs stronger README/SKILL.md context

Recent maintenance

pass

100

23d since push

Alternatives available

pass

82

Alternative skills are available for comparison.