# Critique and audit a built interface for design quality

> Critique and audit a built interface for design quality: 0 companies fully do it, 2 with a limit, 12 carry the tag. Every listing in Design workspaces & canvases with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/design.ui-critique/
- Markdown: https://www.anchorterminal.com/niches/design.ui-critique/index.md (~1,000 tokens)
- Slim: https://www.anchorterminal.com/niches/design.ui-critique/index.min.md (~230 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/design.ui-critique/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 0 | 2 | 12 | 8 | 3 |

## What counts as done

A list of findings, each with a rule id, severity, location (file and line, or selector) and suggested fix, from a run that can be read-only, with an exit status that separates findings from a failed scan.

How agents ask for it: review this page's design; does this look AI-generated; check contrast and spacing; audit our UI for anti-patterns

## Does the job, with a limit

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

- **Impeccable (Renaissance Geek, Inc.)**: detect --json over files, folders or URLs returns findings with rule id, severity, file and line, exiting 0 clean, 2 findings, 1 unscannable. Findings carry a rule description, not a fix; the read-only critique path (acc-34) is merged but unreleased, and acc-15 notes missed patterns.
- **UX Pilot MCP server (UX Pilot)**: review runs UX, persona and accessibility reviews on a screen, raw HTML or a live URL, without applying fixes unless apply is true. Findings' rule ids, severities and locations aren't specified, and reviews cost credits.

- not this job: ArtCraft (Storyteller): No interface audit.
- not this job: Figma API + MCP (Figma, Inc.): No tool audits a built interface for rule-based findings; the server reads and writes Figma files.
- not this job: Framelink MCP for Figma (Framelink (Graham Lipsman)): No audit or rule findings; the tools fetch design data.
- not this job: Framer Server API (Framer B.V.): MCP can review SEO, headings and alt text, but there are no rule ids, severities or exit status for design findings.
- not this job: Kite (Kite): No audit or rule findings tool.
- not this job: Magic Patterns (North Park Labs, Inc.): No audit or rule findings.
- not this job: Melius (Melius AI, Inc.): No interface audit.
- not this job: Miro API + MCP (RealtimeBoard Inc. dba Miro): No interface audit.
- not this job: pen.dev (High Agency, Inc.): No audit tool.
- not this job: Penpot API + MCP (Kaleidos Subsidiary SL): Audits design files, not a built interface.
- not this job: Presentations.AI MCP server (Presentations.AI): No interface audit.
- not this job: Sketch (Sketch B.V.): Audits Sketch documents, not a built interface.
- not this job: Subframe (Atomic Design Inc): No audit of a built interface.
- not this job: UXKIN (UXKIN (no legal entity named)): The no-ui-slop skill guides the agent's own UI work; there is no audit with rule ids or exit status.
- not this job: Zeplin (Zeplin, Inc.): No interface audit.

## What stops agents finishing

- flow requires writes to the repo or questions to a person
- telemetry on by default where policy forbids it

## Around it

Before: code.implement-ui. After: code.edit.

## Where this comes from

Weight 8 of 100 in Design workspaces & canvases: 3 of 42 accounts (Impeccable) plus vendor pages for UX Pilot and Penpot's audit use case

As data: https://www.anchorterminal.com/api/v1/use-cases/design.ui-critique.json, or the MCP tool get_use_case with id design.ui-critique. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
