Agent skill

Product Designer

by borghei in borghei/Claude-Skills

Product design across UI/UX, design systems, prototyping, and user research.

MITAuto-check passedFrontend & Design

Install Product Designer

skills CLI
$ npx skills add borghei/Claude-Skills --skill product-designer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install borghei/Claude-Skills product-designer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/product-team/product-designer .claude/skills/product-designer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
product-designer
GitHub stars
886
Token cost
~3.1k tokens
SKILL.md length
954 words
Files
4 (incl. scripts)
Skills in repo
354
Repo updated
First seen
Licence
MIT

At a glance

Product design across UI/UX, design systems, prototyping, and user research.

  • Works in 5 steps: Discover - Research user needs through… → Define - Synthesize findings into a… → Develop - Ideate solutions through… → …
  • Creating user journey maps
  • SKILL.md covers Clarify First, Workflow, Design Sprint (5-Day Format) and User Journey Map Template, plus 10 more sections
  • Runs Python scripts from its folder; calls python

What it does

Product Designer is an agent skill from borghei/Claude-Skills. Product design across UI/UX, design systems, prototyping, and user research. Use when creating user journey maps, building wireframes, defining design tokens and component systems, planning usability tests, or establishing design principles.

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/design_critique.py`, `scripts/journey_mapper.py` and `scripts/usability_scorer.py`).

It sits in Frontend & Design, covering UI design, UX design and Design tokens. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.

When your agent uses it

  • Creating user journey maps
  • Building wireframes
  • Defining design tokens and component systems
  • Planning usability tests

Example prompts

  • “/product-designer”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Discover - Research user needs through interviews, analytics, and competitive analysis. Create user journey maps and identify pain points…
  2. Define - Synthesize findings into a clear problem statement and design requirements. Build information architecture (card sorting, site…
  3. Develop - Ideate solutions through sketching and wireframing. Build prototypes at appropriate fidelity. Checkpoint: prototype covers the…
  4. Test - Run usability tests with 5-8 participants. Measure task completion rate, time on task, error rate, and SUS score. Checkpoint: all…
  5. Deliver - Refine designs based on test findings. Prepare dev handoff with design tokens, component specs, and interaction documentation…

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Product Designer loads about 3.1k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 954 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 954 words, ~3,092 tokens.

Download SKILL.mdSave it as .claude/skills/product-designer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
product-designer
description
Product design across UI/UX, design systems, prototyping, and user research. Use when creating user journey maps, building wireframes, defining design tokens and component systems, planning usability tests, or establishing design principles.
license
MIT + Commons Clause
metadata.version
1.0.0
metadata.author
borghei
metadata.category
product-design
metadata.domain
product-design
metadata.updated
2026-03-31
metadata.tags
design, ux, ui, figma, prototyping, design-systems

Product Designer

The agent operates as a senior product designer, delivering user-centered design solutions spanning UX research, UI design, design systems, prototyping, and usability testing.

Clarify First

Before generating the design deliverable, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • Target user and the problem — who hurts and the job-to-be-done (drives Discover and the journey map's problem statement)
  • Which deliverable — journey map, wireframe, usability test plan, or design critique (sets which workflow and template applies)
  • Fidelity and stage — exploration vs dev-handoff (drives prototype fidelity and what "done" means)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Workflow

  1. Discover - Research user needs through interviews, analytics, and competitive analysis. Create user journey maps and identify pain points. Checkpoint: problem statement is validated by at least 3 user data points.
  2. Define - Synthesize findings into a clear problem statement and design requirements. Build information architecture (card sorting, site maps). Checkpoint: IA has been validated via card sort or tree test.
  3. Develop - Ideate solutions through sketching and wireframing. Build prototypes at appropriate fidelity. Checkpoint: prototype covers the complete happy path plus one error state.
  4. Test - Run usability tests with 5-8 participants. Measure task completion rate, time on task, error rate, and SUS score. Checkpoint: all critical usability issues are documented with severity ratings.
  5. Deliver - Refine designs based on test findings. Prepare dev handoff with design tokens, component specs, and interaction documentation. Checkpoint: engineering has confirmed feasibility of all interactions.

Design Sprint (5-Day Format)

DayActivityOutput
MondayMap problem, interview expertsChallenge map, target area
TuesdaySketch solutions, Crazy 8sSolution sketches
WednesdayDecide, storyboardTestable hypothesis
ThursdayBuild prototypeRealistic clickable prototype
FridayTest with 5 usersValidated/invalidated hypothesis

User Journey Map Template

PERSONA: Sarah, Product Manager, goal: find analytics insights fast

STAGE:      AWARENESS    CONSIDER     PURCHASE     ONBOARD      RETAIN
Actions:    Searches     Compares     Signs up     Configures   Uses daily
Touchpoint: Google       Website      Checkout     Setup wizard App
Emotion:    Frustrated   Curious      Anxious      Hopeful      Satisfied
Pain point: Too many     Hard to      Complex      Slow setup   Missing
            options      compare      pricing                   features
Opportunity: SEO content  Comparison   Simplify     Quick-start  Feature
                         tool         flow         template     education

Information Architecture

Card Sorting Methods:

  • Open sort: users create their own categories
  • Closed sort: users place items into predefined categories
  • Hybrid: combination approach

Example Site Map:

Home
+-- Products
|   +-- Category A
|   |   +-- Product 1
|   |   +-- Product 2
|   +-- Category B
+-- About
|   +-- Team
|   +-- Careers
+-- Resources
|   +-- Blog
|   +-- Help Center
+-- Account
    +-- Profile
    +-- Settings

UI Design Foundations

Design Principles
  1. Hierarchy - Visual weight guides attention via size, color, and contrast
  2. Consistency - Reuse patterns and components; maintain predictable interactions
  3. Feedback - Acknowledge every user action; show system status and loading states
  4. Accessibility - 4.5:1 color contrast minimum, focus indicators, screen reader support
Design Token System
css
/* Color tokens */
--color-primary-500: #3b82f6;
--color-primary-600: #2563eb;
--color-gray-50: #f9fafb;
--color-gray-900: #111827;
--color-success: #10b981;
--color-warning: #f59e0b;
--color-error: #ef4444;

/* Typography scale */
--text-sm: 0.875rem;   /* 14px */
--text-base: 1rem;     /* 16px */
--text-lg: 1.125rem;   /* 18px */
--text-xl: 1.25rem;    /* 20px */
--text-2xl: 1.5rem;    /* 24px */

/* Spacing (4px base unit) */
--space-1: 0.25rem;    /* 4px */
--space-2: 0.5rem;     /* 8px */
--space-4: 1rem;       /* 16px */
--space-6: 1.5rem;     /* 24px */
--space-8: 2rem;       /* 32px */

Component Structure

Button/
+-- Variants: Primary, Secondary, Tertiary, Destructive
+-- Sizes: Small (32px), Medium (40px), Large (48px)
+-- States: Default, Hover, Active, Focus, Disabled, Loading
+-- Anatomy: [Leading Icon] Label [Trailing Icon]
Component Design Tokens (JSON)
json
{
  "color": {
    "primary": {"50": {"value": "#eff6ff"}, "500": {"value": "#3b82f6"}},
    "semantic": {"success": {"value": "{color.green.500}"}, "error": {"value": "{color.red.500}"}}
  },
  "spacing": {"xs": {"value": "4px"}, "sm": {"value": "8px"}, "md": {"value": "16px"}},
  "borderRadius": {"sm": {"value": "4px"}, "md": {"value": "8px"}, "full": {"value": "9999px"}}
}

Example: Usability Test Plan

markdown
# Usability Test: New Checkout Flow

## Objectives
- Validate that users can complete purchase in < 3 minutes
- Identify friction points in address and payment steps

## Participants
- 6 users (3 new, 3 returning)
- Mix of desktop and mobile

## Tasks
1. "Find a laptop under $1,000 and add it to your cart" (browse + add)
2. "Complete the purchase using a credit card" (checkout flow)
3. "Change the shipping address on your order" (post-purchase edit)

## Success Criteria
| Task | Completion Target | Time Target |
|------|-------------------|-------------|
| Browse + Add | 100% | < 60s |
| Checkout | 90%+ | < 180s |
| Edit address | 80%+ | < 90s |

## Metrics
- Task completion rate
- Time on task
- Error count per task
- System Usability Scale (SUS) score (target: 68+)

Prototype Fidelity Guide

FidelityPurposeToolsTimeline
PaperQuick explorationPaper, penMinutes
Low-fiFlow validationFigma, SketchHours
Mid-fiUsability testingFigmaDays
High-fiDev handoff, final testingFigmaDays-Weeks

Tool Reference

design_critique.py

Evaluates a UI design against Nielsen's 10 Usability Heuristics and accessibility standards. Generates a structured critique report with severity ratings, compliance scores, and prioritized improvement recommendations.

FlagTypeDefaultDescription
--checklistflag-Generate empty checklist for evaluation
--answersstring-Path to completed checklist JSON file
--jsonflagFalseOutput as JSON
bash
python scripts/design_critique.py --checklist
python scripts/design_critique.py --checklist --json > checklist.json
python scripts/design_critique.py --answers completed_checklist.json
python scripts/design_critique.py --answers completed_checklist.json --json
journey_mapper.py

Creates structured user journey maps with emotion curves, pain point identification, and opportunity analysis. Includes pre-built templates for SaaS, e-commerce, and mobile app journeys.

FlagTypeDefaultDescription
--template, -tchoice-Pre-built template: saas, ecommerce, mobile_app
--stages, -sstring-Path to custom stages JSON file
--jsonflagFalseOutput as JSON
bash
python scripts/journey_mapper.py --template saas
python scripts/journey_mapper.py --template ecommerce --json
python scripts/journey_mapper.py --stages custom_journey.json
usability_scorer.py

Calculates System Usability Scale (SUS) scores and task performance metrics from usability test data. Provides individual and aggregate analysis with grade interpretation and benchmarking.

FlagTypeDefaultDescription
actionpositional-"sample" to create sample CSV files
--sus-responsesstring-CSV with SUS responses (participant, q1-q10)
--task-datastring-CSV with task data (participant, task, completed, time_seconds, errors)
--jsonflagFalseOutput as JSON
bash
python scripts/usability_scorer.py sample
python scripts/usability_scorer.py --sus-responses responses.csv
python scripts/usability_scorer.py --task-data tasks.csv
python scripts/usability_scorer.py --sus-responses responses.csv --task-data tasks.csv --json

Show full SKILL.md (358 more words)Show less

Troubleshooting

ProblemCauseSolution
SUS score below 68 (benchmark)Significant usability issuesFocus on critical severity findings from design_critique first
Low task completion rate (<80%)Task flow too complex or unclearSimplify flow; add progressive disclosure; reduce steps
Users cannot find featuresPoor information architectureConduct card sorting; redesign navigation; add search
High error rate on formsInsufficient validation and guidanceAdd inline validation, smart defaults, and contextual help
Inconsistent design across screensMissing or ignored design systemAudit with design_critique; enforce token usage
Usability test participants are unrepresentativePoor recruitment criteriaScreen for target persona match; mix new and returning users
Journey map emotions are flatInsufficient research dataConduct deeper interviews; observe real usage sessions

Success Criteria

CriterionTargetHow to Measure
SUS score>68 (industry average), target >80usability_scorer aggregate score
Task completion rate>85% for core flowsusability_scorer task metrics
Time on task<2x expected durationusability_scorer avg_time_seconds
Design critique compliance>80% checklist pass ratedesign_critique compliance_score
Accessibility complianceWCAG AA on all screensdesign_critique accessibility section
Journey map coverageAll key personas mappedCount of completed journey maps
Usability test cadenceTest every sprint or releaseCount of tests per quarter

Scope & Limitations

In scope:

  • Heuristic evaluation and design critique
  • User journey mapping with emotion curves
  • Usability test scoring (SUS and task metrics)
  • Design sprint facilitation structure
  • Information architecture planning
  • Prototype fidelity guidance
  • Accessibility checkpoint evaluation

Out of scope:

  • Automated visual regression testing (use Chromatic/Percy)
  • Real-time analytics dashboards (use Amplitude/Mixpanel)
  • Figma file manipulation or asset export (use Figma API)
  • Eye tracking or biometric analysis
  • A/B test implementation (see ab-test-setup skill)
  • Design token generation (see ui-design-system or design-system-lead skills)

Integration Points

Tool / PlatformIntegration MethodUse Case
FigmaJourney map and critique findings as design specsTranslate research into design changes
Maze / UserTestingExport task data CSV for usability_scorerScore test results from remote testing platforms
Dovetail / CondensExport interview themes for journey_mapperBuild journey maps from research repositories
Jira / Lineardesign_critique JSON priorities as ticketsTrack usability improvements in sprint backlog
Notion / ConfluenceHuman-readable output from all toolsDocument research findings and design decisions
Miro / FigJamjourney_mapper JSON outputCollaborative journey map workshops

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in product-team/product-designer of borghei/Claude-Skills.

  • SKILL.md
  • scripts/design_critique.py
  • scripts/journey_mapper.py
  • scripts/usability_scorer.py

Open the folder on GitHubat commit 4a698e8

Compare with similar skills

Product Designer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Product Designer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Product Designer this skillborghei/Claude-Skills886—~3.1kAutomated safety check: PassMIT
Prototypeplugin87/ux-ui-agent-skills1.6k—~614Automated safety check: PassMIT
Bmad UXaj-geddes/claude-code-bmad-skills488—~2kAutomated safety check: NotesCustom licence
UI UX Designeraiskillstore/marketplace4307 repos~2.4kAutomated safety check: PassNone
Design Dnazanwei/design-dna1.9k1 repos~2.1kAutomated safety check: PassMIT
Website Design Taste Extractorsenlindesign/taste-skill385—~5.3kAutomated safety check: PassNone

Similar skills

  • Prototype

    plugin87/ux-ui-agent-skills

    Move an idea up the fidelity ladder (content-first → wireframe → low-fi → high-fi → code) with a validation plan at each level, plus user-journey mapping and usability-testing scripts.

    1.6k GitHub stars~614 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Bmad UX

    aj-geddes/claude-code-bmad-skills

    Solutioning-phase UX planning skill (optional; activate when the project has a UI).

    488 GitHub stars~2k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check: notes
  • UI UX Designer

    aiskillstore/marketplace

    Create interface designs, wireframes, and design systems. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 7 repos~2.4k tokens
    Frontend & DesignAuto-check passed
  • Design Dna

    zanwei/design-dna

    Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects…

    1.9k GitHub starsUsed in 1 repo~2.1k tokens
    Frontend & DesignAuto-check passed
  • Website Design Taste Extractor

    senlindesign/taste-skill

    Reverse-engineers a website's design from its URL into a Markdown and JSON pair holding concrete tokens and the trade-offs behind the look.

    385 GitHub stars~5.3k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • Material Design 3 UI/UX Guide

    skydashnet/material-design-3-ui-skill

    Guides designing, reviewing or implementing interfaces that follow Google's Material Design 3 system: semantic tokens, component states, adaptive layout and accessibility.

    135 GitHub stars~3k tokensUpdated 9 days ago
    Frontend & DesignAuto-check passed

More from borghei/Claude-Skills

All 354 skills in this repo
  • Agent Harness

    borghei/Claude-Skills

    Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets.

    886 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed
  • Agents In The Team

    borghei/Claude-Skills

    Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.

    886 GitHub stars~4.2k tokensUpdated 2 days ago
    Auto-check passed
  • AI Content Disclosure

    borghei/Claude-Skills

    Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.

    886 GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed
  • AI Prototyping

    borghei/Claude-Skills

    Idea to AI-generated prototype to customer validation to engineering handoff.

    886 GitHub stars~3.6k tokensUpdated 2 days ago
    Auto-check passed
  • Analytics Engineer

    borghei/Claude-Skills

    Analytics engineering across data modeling, dbt, transformation, and semantic layers.

    886 GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed
  • Ansoff Matrix

    borghei/Claude-Skills

    Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.

    886 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed

Questions about Product Designer

What does Product Designer do?

Product design across UI/UX, design systems, prototyping, and user research. Product Designer is an agent skill from borghei/Claude-Skills. Product design across UI/UX, design systems, prototyping, and user research.

When should I use Product Designer?

Product Designer fits situations like: creating user journey maps; building wireframes; defining design tokens and component systems; planning usability tests.

How do I install Product Designer in Claude Code?

Run `npx skills add borghei/Claude-Skills --skill product-designer -a claude-code`. Or copy the skill folder (product-team/product-designer in borghei/Claude-Skills) into .claude/skills/product-designer in your project. Claude Code loads it when a task matches its description.

How do I install Product Designer in Codex?

Run `npx skills add borghei/Claude-Skills --skill product-designer -a codex`. Or copy the skill folder (product-team/product-designer in borghei/Claude-Skills) into .agents/skills/product-designer in your project. Codex loads it when a task matches its description.

Can I use Product Designer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill product-designer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-designer, .gemini/skills/product-designer, .github/skills/product-designer and .opencode/skills/product-designer in your project.

What does Product Designer need to run?

Going by SKILL.md and its folder, Product Designer needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Product Designer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Product Designer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Product Designer use?

Product Designer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Product Designer use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Product Designer?

Skills that share tags, products or a category with Product Designer: Prototype (plugin87/ux-ui-agent-skills, 1.6k stars), Bmad UX (aj-geddes/claude-code-bmad-skills, 488 stars), UI UX Designer (aiskillstore/marketplace, 430 stars) and Design Dna (zanwei/design-dna, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Designer?

borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 886 GitHub stars. The repository holds 354 skills in this directory. The repository was last updated on October 7, 2026.

Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.