Critique a product surface against its actual user task, evidence hierarchy, affordances, motion, accessibility, and visual coherence; deliver specific fixes and verify them on the live surface.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Design Critique
Use `design-taste` for the project's visual and product standards. Review the
actual surface at the user's viewport, not a component screenshot alone.
1. Name the user decision the surface should improve and what evidence makes
that decision better. If the surface is a graph, trace a visible relationship
to its sources, confidence, competing explanations, and an actionable
workflow. A decorative graph without this path is not complete.
2. Walk the primary task, its failure state, settings, navigation, and return
path. Test keyboard access, focus order, contrast, motion preferences, and
small screens.
3. Rank findings by user consequence and cite the exact screen or interaction.
Separate observed defects from taste judgments and unknowns.
4. Implement the smallest coherent correction in the intended repository.
Revisit the live surface after the change; capture evidence for each fixed
high-severity finding.
Do not label static animation as capability. Motion should show state or
causality and stop or simplify when reduced motion is requested.
The line at the top of this page pins the label git:20261024.d21bd85, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1355 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
tcuzzo/backs-aios-skills · 2 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_haleszyg6d54vpcf
GET https://markdownregistry.com/api/v1/resolve?ref=tcuzzo/backs-aios-skills/design-critique
GET https://markdownregistry.com/api/v1/blob/d3e1b252fb72d34bb7f75422b1fc1a082631e71a5d0d4b476f21e6b15de6440b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
tcuzzo/backs-aios-skills · claude-skills/provider/SKILL.md · Configure Claude, Ollama, MiniMax, or Needle/Kev Automatic routing through the configured gateway for the next local…
tcuzzo/backs-aios-skills · i18n/de/skills/absorb/SKILL.md · Nutze das, wenn du eine Fähigkeit brauchst, die ein Open-Source-Projekt schon liefert — übernimm sie und baue sie als…
tcuzzo/backs-aios-skills · i18n/de/skills/backs-pack-sync/SKILL.md · Compare private BACKS runtime skill coverage with the public AIOS pack without disclosing names or content. Add a…
tcuzzo/backs-aios-skills · i18n/de/skills/blind-eval/SKILL.md · Nutze das vor dem Landen von allem, wo Geschmack oder Output-Qualität die Frage ist und kein Test entscheiden kann…
tcuzzo/backs-aios-skills · i18n/de/skills/blind-tribunal/SKILL.md · Nutze das, wenn eine autonome Änderung vor dem Landen eine unabhängige Bewertung braucht und kein Mensch in der…
tcuzzo/backs-aios-skills · i18n/de/skills/bounded-loops/SKILL.md · Nutze das vor jeder Schleife, die retrien, pollen, iterieren oder eine externe API rufen kann — Agent-Loops…
tcuzzo/backs-aios-skills · i18n/de/skills/building-with-backs/SKILL.md · Build or repair a BACKS project at the operator's intended repository and path, with a checked source revision, one…
adityareddy-dev/deskstudio · skills/design-critique/SKILL.md · A heuristic critique of a screen or flow against the Nielsen ten usability heuristics plus the studio rubric, from a…
qa-aman/claude-skills · skills/by-role/designer/design-critique/SKILL.md · Critique a design for usability, hierarchy, and accessibility. Use when the user says "critique this design", "review…
skillmedev/skills · skills/design-critique/SKILL.md · Runs a structured design critique of a screen, flow, or component across three dimensions - jobs-to-be-done, clarity…
amey-thakur/ai-skills · skills/big-tech-processes/design-critique/SKILL.md · Run a design critique with a clear presenter contract, feedback rules that attack the work not the person, and captured…
tekkiiiii/the-agency · skills/design-critique/SKILL.md · Use for UI/UX design review: "review design", "critique this UI", "audit the design", "check this Figma", "review this…
