- Home
- Skills
- UX & UI Design
- ♿ Accessibility Evidence Freshness Auditor
More screenshots
Works with the AI Agents you already use
♿ Accessibility Evidence Freshness Auditor
Check whether accessibility conformance claims still trace to current, scoped, version-matched, manually reviewed, and retested evidence.
$19
♿ Accessibility Evidence Freshness Auditor
Example session with this skill installed
A support claim for mobile version 3.0 cites a 2025 automated failure from web version 1.0, has no owner or manual test, and its closed issue has no retest.
- Read your context and instructions
- Compiled the accessibility evidence freshness
Gate: BLOCK. Stale evidence, scope and version mismatches, contradictory result, missing owner and manual evidence, and unretested fix require qualified review.
Connects securely to your tools. The creator never sees your data.
About this skill
Accessibility Evidence Freshness Auditor reconciles a claim ledger with dated test evidence, product scope, release version, manual-test requirements, and issue retest records. It surfaces stale, missing, mismatched, contradictory, or unretested evidence and returns a claim ledger, findings, JSON qualified-review gate, and memo. It never generates or certifies an ACR or decides WCAG conformance.
What it produces
- Claim-to-evidence lineage ledger
- Freshness, scope, version, and retest findings
- JSON qualified-review gate
- Accessibility-owner review memo
Use cases
- Review an existing ACR claim set for a new release
- Catch stale or version-mismatched accessibility evidence
- Require manual evidence for recorded support claims
- Find closed issues that lack passing retest evidence
Known limitations
- The tool does not test a product, generate an ACR, or certify WCAG, ADA, Section 508, or EAA compliance.
- Manual-test type requirements come from the supplied policy and remain organization-specific.
- A ready result means evidence lineage is reviewable, not that the product conforms.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for UX & UI Design.
The tool does not test a product, generate an ACR, or certify WCAG, ADA, Section 508, or EAA compliance. Manual-test type requirements come from the supplied policy and remain organization-specific. A ready result means evidence lineage is reviewable, not that the product conforms.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Permissions
File Scopes
The deterministic helper reads supplied local evidence and writes only to the selected audit output directory.