Setup & Installation
openclaw skills install @hajekt2/ua1-validator-agent
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install ua1-validator-agent
What This Skill Does
Runs PDF/UA-1 accessibility validation against the ua1.dev API from within agent workflows. Returns machine-readable verdicts with findings grouped by rule ID. Designed for CI gating and automated remediation loops.
Returns deterministic exit codes and compact structured verdicts that CI pipelines can consume directly, without manual review of accessibility reports.
When to use it
- Blocking non-accessible PDFs in a CI pipeline before release
- Batch-checking generated PDFs for accessibility rule failures
- Getting a remediation plan sorted by most frequent violations
- Re-validating a PDF after fixes to confirm issues are resolved
- Integrating accessibility checks into a document generation workflow
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Check if report.pdf passes PDF/UA-1
AGENT
- 1Run health check against api.ua1.dev/api/health
- 2POST report.pdf to api.ua1.dev/api/validate?format=compact
- 3Parse verdict field from the response
- 4If verdict is fail, group findings by rule_id sorted by frequency
- 5Return prioritized remediation plan based on rule violations
OUTPUT
Pass/fail verdict with grouped rule violations and a prioritized remediation list