{
 "schema": "aiblocks-page/1",
 "id": "agency-design-ui-finish-gate-reviewer",
 "type": "agent",
 "name": "Interface finishing reviewer",
 "summary": "Get a clear PASS or HOLD on a built screen before release, with the generic UI patterns found and the exact fixes to check.",
 "headline": "Interface finishing reviewer",
 "subhead": "Share your built screens at desktop and phone size, and say who uses them and what they do there. The agent writes a short design contract, then checks the real screens against it. You get a PASS or HOLD call and a fix list, with how to verify each fix.",
 "job": {
  "id": "design-work",
  "name": "Design things people love"
 },
 "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": "design_file",
   "required": false,
   "label": "Design file",
   "what": "a design in a design tool, such as a Figma file, with its parts and styles"
  },
  {
   "type": "web_page",
   "required": false,
   "label": "Web page",
   "what": "a built or live web page, as a URL or saved HTML"
  },
  {
   "type": "codebase",
   "required": false,
   "label": "Codebase",
   "what": "a project's code, in a folder or repo the AI can open"
  },
  {
   "type": "image",
   "required": false,
   "label": "Image",
   "what": "a finished picture"
  }
 ],
 "outputs": [
  {
   "type": "audit_report",
   "required": true,
   "label": "Audit report",
   "what": "findings with evidence, severity, missing inputs and next actions"
  }
 ],
 "you_give": [
  "Screenshots of the built screens at desktop and phone width, or live links",
  "Who uses each screen and the one thing they come to do",
  "Brand, framework or design rules you must keep (optional)",
  "Screens in their loading, empty and error states (optional)",
  "Products you admire, or want to look different from (optional)"
 ],
 "you_get": [
  "A short design contract for each screen, with what is seen first, the main action and the forbidden defaults",
  "A HOLD or PASS call for desktop and for phone, or NOT RATED if you did not show enough",
  "Findings with the evidence and the reason each one breaks the contract",
  "A required change for each finding, and the state or screen width to check it at",
  "A list of choices that already work, so nobody rewrites them",
  "PASS criteria for the next review"
 ],
 "use_when": [
  "A screen is built and about to go live, and someone should ask hard questions first.",
  "The screen works but feels like \"any SaaS\", or looks AI-made.",
  "You need a clear go or no-go before a release or a demo.",
  "The phone version only stacks the desktop layout, and you suspect it hides the main job."
 ],
 "skip_when": [
  "You want a 0 to 100 score for how AI-made your UI code looks. Use the UI design consistency reviewer.",
  "You want every new screen reviewed with several checks each time. Use the Screen usability reviewer.",
  "You want a new design, not a review. Use the UI Designer agent."
 ],
 "output_sample": {
  "input": [
   "Screenshots of your built screens at desktop and phone width",
   "Who uses each screen and what they come to do",
   "Brand or framework rules you must keep (optional)",
   "Loading, empty and error states (optional)"
  ],
  "prerequisites": [
   "An AI that can read images, such as Claude, ChatGPT or Gemini"
  ],
  "output": [
   {
    "name": "Design contract",
    "contains": "Who uses the screen, what is seen first, the main action, density and forbidden defaults."
   },
   {
    "name": "Decision",
    "contains": "PASS or HOLD for desktop and for phone, or NOT RATED if not enough was shown."
   },
   {
    "name": "Evidence",
    "contains": "Each issue seen on the screen and why it breaks the contract."
   },
   {
    "name": "Required before PASS",
    "contains": "Numbered changes, each with the state or screen width to check it at."
   },
   {
    "name": "Keep list",
    "contains": "Choices that already work and should not be rewritten."
   },
   {
    "name": "PASS criteria",
    "contains": "What must be true for the screen to pass the next review."
   },
   {
    "name": "Open checks",
    "contains": "What could not be judged from the files you shared."
   }
  ]
 },
 "output_shape": "DESIGN CONTRACT <screen>\n  User and job <who finishes what> | Seen first <object> | Main action <one action>\n  Density <compact, balanced or spacious, and why> | Forbidden defaults <list>\n\nFINISH GATE <screen> | DECISION <PASS, HOLD or NOT RATED>\n\nEVIDENCE\n  <what you can see> -> <why it breaks the contract>\n\nREQUIRED BEFORE PASS\n  <number>. <change> | verify at <state or screen width>\n\nKEEP\n  <choice that works>\n\nPASS CRITERIA\n  <check>\n\nOPEN CHECKS\n  <what could not be seen from the files>",
 "how_to_use": [
  "Add the pack to your AI as a skill. If you cannot, start a new chat and paste SKILL.md, then references/source-agent.md.",
  "Attach screenshots at desktop and phone width. Say who uses the screen and what they come to do.",
  "Say what must stay, such as your brand, framework or existing parts.",
  "Read the design contract first. Correct any wrong guess about the user or the main action before you read the findings.",
  "Fix everything under \"Required before PASS\". Run it again with new screenshots to get the PASS call.",
  "Keep the \"Keep\" list. It names the choices that already serve your product."
 ],
 "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": "Product-specific interface designer",
   "url": "https://useaiblocks.com/skills/product-true-ui-designer",
   "why": "Design it"
  }
 ],
 "source": {
  "by": "Michael Sitarzewski and Agency Agents contributors",
  "repo": "msitarzewski/agency-agents",
  "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/design/design-ui-finish-gate-reviewer.md",
  "licence": "MIT",
  "original_name": "UI Finish-Gate Reviewer",
  "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219"
 },
 "credits": [
  {
   "title": "UI Finish-Gate Reviewer",
   "by": "Michael Sitarzewski and Agency Agents contributors",
   "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/design/design-ui-finish-gate-reviewer.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-design-ui-finish-gate-reviewer",
  "markdown": "https://useaiblocks.com/agents/agency-design-ui-finish-gate-reviewer.md",
  "json": "https://useaiblocks.com/agents/agency-design-ui-finish-gate-reviewer.json",
  "instructions": "https://useaiblocks.com/skills/agency-design-ui-finish-gate-reviewer/SKILL.md",
  "download": "https://useaiblocks.com/skills/agency-design-ui-finish-gate-reviewer.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/agency-design-ui-finish-gate-reviewer",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-design-ui-finish-gate-reviewer",
  "mcp": "https://useaiblocks.com/mcp"
 }
}