PRD to UX Translation

VerifiedSafe

Transform product requirements into UX foundations via 6 forced designer mindset passes. Ensures mental models and info architecture precede visual design.

Sby Skills Guide Bot
ProductivityIntermediate
7/25/2026
Claude Code
#ux-design#prd-analysis#design-handoff#information-architecture#cognitive-load

Recommended for

Automated summary

Translates product requirements from a PRD into UX foundations through six structured designer mindset passes before any visual specifications.

Strengths

  • Enforces six ordered passes covering mental models, information architecture, affordances, cognitive load, states, and flow integrity before visuals.
  • Writes a persistent UX spec file alongside the source PRD for mockup and design handoff.
  • Includes explicit guardrails, including an iron law and red flags, that prevent skipping foundational analysis.
  • Surfaces often-missed issues such as misconceptions, progressive disclosure, state matrices, and flow risks.

Limitations

  • Does not create mockups, UI code, or a visual design system; it stops at foundations and specifications.
  • Output quality depends heavily on the completeness and accuracy of the source PRD.
  • Six passes may be excessive for tiny features or disposable prototypes.
When to use it

Use when a PRD needs to become UX foundations and a design handoff before mockups are created.

When not to use it

Avoid when you need immediate screens, visual mockups, or UI code without a UX analysis phase.

Security analysis

Safe
Quality score86/100

This is a pure instruction/methodology document for translating PRDs into UX specs. It declares no tools, contains no shell commands, no network access, no credential handling, no obfuscated payloads, and no destructive operations. Its only side effect is writing a markdown spec file next to the source PRD, which is benign and explicitly described. No safety mechanisms are disabled and no external data is transmitted.

No concerns found

How this analysis is made

Examples

PRD to UX spec
Create UX specs from feature-x.md. Run all 6 designer mindset passes in order and write the result to feature-x-ux-spec.md. Do not include visual specs until all passes are complete.
Design handoff prep
Translate PRD.md into UX foundations and prepare a design handoff. Cover mental models, information architecture, affordances, cognitive load, states, and flow risks before any screen layouts.
Mockup readiness
We need to prepare for mockups for our new onboarding flow. Use the PRD at onboarding-prd.md to create a UX spec with the 6 forced passes, then add visual specifications only after Pass 6.

name: prd-ux description: This skill should be used when the user asks to "create UX specs", "translate PRD to UX", "design user experience", "prepare for mockups", "create design handoff", or needs to transform product requirements into UX foundations. Uses 6 forced designer mindset passes before any visual specifications.

PRD to UX Translation

Translate product requirements into UX foundations through 6 forced designer mindset passes. Each pass asks questions that visual-first approaches skip.

Core principle: UX foundations come BEFORE visual specifications. Mental models, information architecture, and cognitive load analysis prevent "pretty but unusable" designs.

The Iron Law

NO VISUAL SPECS UNTIL ALL 6 PASSES COMPLETE

Not negotiable:

  • Don't mention colors, typography, or spacing until Pass 6 is done
  • Don't describe screen layouts until information architecture is explicit
  • Don't design components until affordances are mapped

No exceptions for urgency:

  • "I'm in a hurry" → Passes take 5 minutes; fixing bad UX takes days
  • "Just give me screens" → Screens without foundations need rework
  • "Skip the analysis" → Analysis IS the value; screens are just output

Output Location

Write UX spec to same directory as source PRD:

  • PRD feature-x.md → output feature-x-ux-spec.md
  • PRD PRD.md → output UX-spec.md

Always write to file for persistence and mockup tool handoff.

The 6 Passes

Execute IN ORDER. Each pass produces required outputs before the next begins.

Pass 1: User Intent & Mental Model

Mindset: "What does the user think is happening?"

Force:

  • What does the user believe this system does?
  • What are they trying to accomplish in one sentence?
  • What wrong mental models are likely?

Output: Primary intent, likely misconceptions, UX principles to reinforce.

Pass 2: Information Architecture

Mindset: "What exists, and how is it organized?"

Force:

  1. Enumerate ALL concepts the user will encounter
  2. Group into logical buckets
  3. Classify each as: Primary / Secondary / Hidden

Output: Concept list, grouped structure, navigation hierarchy.

Pass 3: Affordances & Action Clarity

Mindset: "What actions are obvious without explanation?"

Force:

  • What is clickable?
  • What looks editable?
  • What looks like output (read-only)?
  • What looks final vs in-progress?

Output: Action-signal mapping, affordance rules.

Pass 4: Cognitive Load & Decision Minimization

Mindset: "Where will the user hesitate?"

Identify:

  • Moments of choice (decisions required)
  • Moments of uncertainty (unclear what to do)
  • Moments of waiting (system processing)

Apply:

  • Collapse decisions (fewer choices)
  • Delay complexity (progressive disclosure)
  • Introduce defaults (reduce decision burden)

Output: Friction points table, defaults list.

Pass 5: State Design & Feedback

Mindset: "How does the system talk back?"

For EACH major element, enumerate:

  • Empty
  • Loading
  • Success
  • Partial
  • Error

For each state: What does user see, understand, and can do?

Output: State matrix for each element/screen.

Pass 6: Flow Integrity Check

Mindset: "Does this feel inevitable?"

Check:

  • Where could users get lost?
  • Where would a first-time user fail?
  • What must be visible vs can be implied?

Output: Flow risks table, visibility decisions, UX constraints.

THEN: Visual Specifications

Only after all 6 passes, create:

  • Screen layouts
  • Component specifications
  • Design system
  • Interaction specifications
  • Responsive breakpoints

Red Flags - STOP and Restart

| Violation | What You're Skipping | | ------------------------------------------ | ------------------------------ | | Describing colors/fonts | All foundational passes | | "The main screen shows..." | Pass 1-2 (mental model, IA) | | Designing components before actions mapped | Pass 3 (affordances) | | No friction point analysis | Pass 4 (cognitive load) | | States only in component specs | Pass 5 (holistic state design) | | No "where could they fail?" | Pass 6 (flow integrity) |


Additional Resources

Reference Files

For detailed techniques and patterns:

  • references/pass-enhancements.md — Advanced techniques for each pass
  • references/state-choreography.md — Transition design, feedback patterns
  • references/affordance-patterns.md — Z-index, touch targets, component consolidation
  • references/failure-modes.md — Error mapping, recovery paths

Example Files

Working examples in examples/:

  • complete-ux-spec.md — Full 6-pass example for a task manager

Quick Reference

Pass Output Summary

| Pass | Mindset | Key Output | | ---- | ------------------- | ---------------------------- | | 1 | What user thinks | Mental model, misconceptions | | 2 | What exists | IA structure, navigation | | 3 | What's obvious | Affordance mapping | | 4 | Where hesitation | Friction points, defaults | | 5 | How system responds | State matrices | | 6 | Where they fail | Risk mitigation, constraints |

State Design Quick Matrix

| State | User Sees | User Understands | User Can Do | | ------- | --------- | ---------------- | ----------- | | Empty | [Visual] | [Meaning] | [Actions] | | Loading | [Visual] | [Meaning] | [Actions] | | Success | [Visual] | [Meaning] | [Actions] | | Partial | [Visual] | [Meaning] | [Actions] | | Error | [Visual] | [Meaning] | [Actions] |

Success Feedback Pattern

Action → Success indicator → Hold 300-500ms → Proceed

Users must SEE success before UI transitions.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/prd-to-ux-translation-mrzxuov4/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/prd-to-ux-translation-mrzxuov4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/prd-to-ux-translation-mrzxuov4/download' --output '.skill-downloads/prd-to-ux-translation-mrzxuov4/SKILL.md.part' && mv '.skill-downloads/prd-to-ux-translation-mrzxuov4/SKILL.md.part' '.skill-downloads/prd-to-ux-translation-mrzxuov4/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Original excerpt: Quick Reference

Pass Output Summary

PassMindsetKey Output
1What user thinksMental model, misconceptions
2What existsIA structure, navigation
3What's obviousAffordance mapping
4Where hesitationFriction points, defaults
5How system respondsState matrices
6Where they failRisk mitigation, constraints

State Design Quick Matrix

StateUser SeesUser UnderstandsUser Can Do
Empty[Visual][Meaning][Actions]
Loading[Visual][Meaning][Actions]
Success[Visual][Meaning][Actions]
Partial[Visual][Meaning][Actions]
Error[Visual][Meaning][Actions]

Success Feedback Pattern

Action → Success indicator → Hold 300-500ms → Proceed

Users must SEE success before UI transitions.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/prd-to-ux-translation-mrzxuov4/SKILL.md' && test -s '.skill-downloads/prd-to-ux-translation-mrzxuov4/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/prd-ux' && cp -R '.skill-downloads/prd-to-ux-translation-mrzxuov4' '.claude/skills/prd-ux'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/prd-to-ux-translation-mrzxuov4'

openskills read 'prd-to-ux-translation-mrzxuov4'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/prd-to-ux-translation-mrzxuov4/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills