{ "schema": "aiblocks-page/1", "id": "agency-testing-accessibility-auditor", "type": "agent", "name": "Accessibility auditor", "summary": "Audit a web page or app for accessibility barriers. Get findings tied to WCAG 2.2, a test plan for keyboard and screen readers, and a fix list.", "headline": "Accessibility auditor", "subhead": "Share the pages or flows in scope, the code or screenshots, and the level you are aiming for. It reports barriers by WCAG rule and severity with a fix for each, and writes the keyboard and screen reader tests a person must run to confirm them.", "job": { "id": "test-and-fix-code", "name": "Test and fix code" }, "level": "intermediate", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-26", "inputs": [ { "type": "question", "required": true, "label": "Question", "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like" }, { "type": "web_page", "required": false, "label": "Web page", "what": "a built or live web page, as a URL or saved HTML" } ], "outputs": [ { "type": "audit_report", "required": true, "label": "Audit report", "what": "findings with evidence, severity, missing inputs and next actions" }, { "type": "test_report", "required": true, "label": "Test report", "what": "what was tested, what passed, what failed and why" } ], "you_give": [ "The pages or flows in scope, such as \"sign up and check out\", as a link, HTML or screenshots", "The level you are aiming for, such as WCAG 2.2 AA (it assumes this if you do not say)", "The tools you can use, such as a scanner, a screen reader or just a keyboard", "Your tech stack, such as React or plain HTML (optional)", "Barriers users have already reported (optional)" ], "you_get": [ "A list of barriers, each with the WCAG rule, severity, who it affects, location and fix", "A result for each rule in scope, either pass, fail, not tested or not applicable", "A plain verdict of does not conform, not determined or conforms, with what was left untested", "A keyboard test checklist and a screen reader test script for your key flows", "A fix order, with the quick wins marked" ], "use_when": [ "You are about to launch a site, app or feature and want an accessibility check first.", "A customer, school or partner asks for proof that your product is accessible.", "A scan came back clean, but a user says they could not use a form or menu.", "You built a custom tab, menu or pop-up, and want to know if it works for screen reader and keyboard users." ], "skip_when": [ "You are a U.S. government body or contractor and need a Section 508 report. Use the Section 508 accessibility reviewer.", "You need a legal certificate of conformance. Only a qualified auditor can give one.", "You want the page fixed and rebuilt. Take the findings to the Frontend developer, or fix them yourself in your code.", "You want a general quality check of how a site looks and works. Use the Visual QA evidence collector." ], "output_sample": { "input": [ "The pages or flows in scope, as a link, HTML or screenshots", "The standard and level you are aiming for", "The tools you can use for testing", "Your tech stack and reported barriers (optional)" ], "prerequisites": [ "A keyboard, and a screen reader such as NVDA or VoiceOver, for the manual tests", "A scanner such as axe or Lighthouse, if you want the automated pass" ], "output": [ { "name": "Scope", "contains": "The pages, flows, standard and tools, plus what was assumed or missing." }, { "name": "Results by rule", "contains": "Pass, fail, not tested or not applicable for each WCAG rule in scope, with evidence." }, { "name": "Findings", "contains": "Each barrier with rule, severity, who it affects, location, current code, fix and how to verify." }, { "name": "Verdict", "contains": "Does not conform, not determined or conforms, and the scope left untested." }, { "name": "Tests to run", "contains": "A keyboard checklist, a screen reader script, and zoom and motion checks for your flows." }, { "name": "Fix order", "contains": "Items to fix now, next and later, plus the patterns worth keeping." } ] }, "output_shape": "SCOPE\n product | pages and flows | standard | tools used | ASSUMED: | MISSING: \n\nRESULTS BY RULE\n | PASS, FAIL, NOT TESTED or NOT APPLICABLE | evidence\n\nFINDINGS\n | | WCAG <rule> | severity <critical, serious, moderate, minor>\n who it affects <users> | location <page, part> | evidence <what> | current <code> | fix <code> | how to verify <test> | status <seen, to test>\n\nVERDICT\n <DOES NOT CONFORM, NOT DETERMINED or CONFORMS> | why | untested scope <list>\n\nTESTS TO RUN\n keyboard checklist | screen reader script | zoom and reflow | reduced motion and contrast\n\nFIX ORDER\n immediate <list> | next sprint <list> | ongoing <list> | what is working well <list>", "how_to_use": [ "Download the pack from this page and add it to your AI as a skill. Or paste SKILL.md into a new chat, then paste references/source-agent.md after it.", "List the pages and flows in scope, say the level you are aiming for, and paste the code or screenshots. Say which tools you have. A chat AI cannot open your site, so paste what it should check.", "Read the plan. Run the scanner if it lists one, then the keyboard test. Use a screen reader for the key flows, such as NVDA on Windows or VoiceOver on Mac.", "Paste your results into the chat, one flow at a time. Ask the agent to update the findings and the verdict.", "Fix the critical and serious items in your code first. Run the same tests again to prove each fix.", "Keep the final report with your release notes. Plan a re-check after big changes." ], "checks": [ "The result addresses your actual task and cites the evidence used.", "Examples, role-play experience and targets are kept separate from verified results.", "Claims of tests, memory, tool access or completed actions match what actually happened." ], "next": [ { "name": "Web accessibility checker", "url": "https://useaiblocks.com/skills/accessibility-checker", "why": "Web accessibility checker" }, { "name": "Test results analyst", "url": "https://useaiblocks.com/skills/agency-testing-test-results-analyzer", "why": "Test results analyst" }, { "name": "Bug root cause finder", "url": "https://useaiblocks.com/skills/bug-root-cause-finder", "why": "Bug root cause finder" } ], "source": { "by": "Michael Sitarzewski and Agency Agents contributors", "repo": "msitarzewski/agency-agents", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/testing/testing-accessibility-auditor.md", "licence": "MIT", "original_name": "Accessibility Auditor", "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219" }, "credits": [ { "title": "Accessibility Auditor", "by": "Michael Sitarzewski and Agency Agents contributors", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/testing/testing-accessibility-auditor.md", "used": "Original agent profile, preserved in references/source-agent.md; AI Blocks adds setup and review instructions." } ], "files": [ "LICENSE", "references/source-agent.md", "SETUP.md", "source.json" ], "links": { "page": "https://useaiblocks.com/agents/agency-testing-accessibility-auditor", "markdown": "https://useaiblocks.com/agents/agency-testing-accessibility-auditor.md", "json": "https://useaiblocks.com/agents/agency-testing-accessibility-auditor.json", "instructions": "https://useaiblocks.com/skills/agency-testing-accessibility-auditor/SKILL.md", "download": "https://useaiblocks.com/skills/agency-testing-accessibility-auditor.zip", "api_item": "https://useaiblocks.com/api/v1/items/agency-testing-accessibility-auditor", "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-testing-accessibility-auditor", "mcp": "https://useaiblocks.com/mcp" } }