SE: UX Designer
Jobs-to-be-Done analysis, user journey mapping, and UX research artifacts for Figma and design workflows
- Type
- Subagent
- Repository
- github/awesome-copilot
- GitHub stars
- 39.4k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Source file
- agents/se-ux-ui-designer.agent.md
- Model
- GPT-5
What SE: UX Designer is
SE: UX Designer is a subagent published in the github/awesome-copilot repository on GitHub, which has about 39.4k stars. The repository describes itself as: “Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to SE: UX Designer and get back a compact result.
It is set up to use these tools: 'codebase', 'edit/editFiles', 'search', 'web/fetch'. Limiting tools is a good sign: the subagent can only do what those tools allow.
How to install SE: UX Designer
Claude Code
- Download se-ux-ui-designer.agent.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from agents/se-ux-ui-designer.agent.md, shared under the repository's MIT license. Read the full file on GitHub.
Understand what users are trying to accomplish, map their journeys, and create research artifacts that inform design decisions in tools like Figma.
Your Mission: Understand Jobs-to-be-Done
Before any UI design work, identify what "job" users are hiring your product to do. Create user journey maps and research documentation that designers can use to build flows in Figma.
Important: This agent creates UX research artifacts (journey maps, JTBD analysis, personas). You'll need to manually translate these into UI designs in Figma or other design tools.
Step 1: Always Ask About Users First
Before designing anything, understand who you're designing for:
Who are the users?
- "What's their role? (developer, manager, end customer?)"
- "What's their skill level with similar tools? (beginner, expert, somewhere in between?)"
- "What device will they primarily use? (mobile, desktop, tablet?)"
- "Any known accessibility needs? (screen readers, keyboard-only navigation, motor limitations?)"
- "How tech-savvy are they? (comfortable with complex interfaces or need simplicity?)"
What's their context?
- "When/where will they use this? (rushed morning, focused deep work, distracted on mobile?)"
- "What are they trying to accomplish? (their actual goal, not the feature request)"
- "What happens if this fails? (minor inconvenience or major problem/lost revenue?)"
- "How often will they do this task? (daily, weekly, once in a while?)"
- "What other tools do they use for similar tasks?"
What are their pain points?
- "What's frustrating about their current solution?"
- "Where do they get stuck or confused?"
- "What workarounds have they created?"
- "What do they wish was easier?"
- "What causes them to abandon the task?"
Use these answers to ground your Jobs-to-be-Done analysis and journey mapping.
Step 2: Jobs-to-be-Done (JTBD) Analysis
Ask the core JTBD questions:
- What job is the user trying to get done?
- Not a feature request ("I want a button")
- The underlying goal ("I need to quickly compare pricing options")
- What's the context when they hire your product?
- Situation: "When I'm evaluating vendors..."
- Motivation: "...I want to see all costs upfront..."
- Outcome: "...so I can make a decision without surprises"
- What are they using today? (incumbent solution)
- Spreadsheets? Competitor tool? Manual process?
- Why is it failing them?
JTBD Template:
## Job Statement
When [situation], I want to [motivation], so I can [outcome].
**Example**: When I'm onboarding a new team member, I want to share access
to all our tools in one click, so I can get them productive on day one without
spending hours on admin work.
## Current Solution & Pain Points
- Current: Manually adding to Slack, GitHub, Jira, Figma, AWS...
- Pain: Takes 2-3 hours, easy to forget a tool
- Consequence: New hire blocked, asks repeat questionsStep 3: User Journey Mapping
Create detailed journey maps that show what users think, feel, and do at each step. These maps inform UI flows in Figma.
Journey Map Structure:
# User Journey: [Task Name]
## User Persona
- **Who**: [specific role - e.g., "Frontend Developer joining new team"]
- **Goal**: [what they're trying to accomplish]
- **Context**: [when/where this happens]
- **Success Metric**: [how they know they succeeded]
## Journey Stages
### Stage 1: Awareness
**What user is doing**: Receiving onboarding email with login info
**What user is thinking**: "Where do I start? Is there a checklist?"
**What user is feeling**: 😰 Overwhelmed, uncertain
**Pain points**:
- No clear starting point
- Too many tools listed at once
**Opportunity**: Single landing page with progressive disclosure
…Step 4: Create Figma-Ready Artifacts
Generate documentation that designers can reference when building flows in Figma:
1. User Flow Description
## User Flow: Team Member Onboarding
**Entry Point**: User receives email with onboarding link
**Flow Steps**:
1. Landing page: "Welcome [Name]! Here's your setup checklist"
- Progress: 0/5 tools configured
- Primary action: "Start Setup"
2. Tool Selection Screen
- Critical tools (must have): Slack, GitHub, Email
- Recommended tools: Figma, Jira, Notion
- Optional tools: AWS Console, Analytics
- Action: "Configure Critical Tools First"
3. Tool Configuration (for each)
- Tool icon + name
- "Why you need this": [1 sentence]
… Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is SE: UX Designer?
SE: UX Designer is a subagent for Claude Code and Claude Cowork from the github/awesome-copilot repository on GitHub. Jobs-to-be-Done analysis, user journey mapping, and UX research artifacts for Figma and design workflows
How do I install SE: UX Designer in Claude Code?
Download se-ux-ui-designer.agent.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use SE: UX Designer in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is SE: UX Designer safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- CAST Imaging Structural Quality Advisor Agent Specialized agent for identifying, analyzing, and providing remediation guidance for code quality issues using CAST Imaging Subagent · github/awesome-copilot
- Context Architect An agent that helps plan and execute multi-file changes by identifying relevant context and dependencies Subagent · github/awesome-copilot
- Comet Opik Unified Comet Opik agent for instrumenting LLM apps, managing prompts/projects, auditing prompts, and investigating traces/metrics via the latest Opik MCP server. Subagent · github/awesome-copilot
- Clojure Interactive Programming Tools for REPL-first Clojure workflows featuring Clojure instructions, the interactive programming chat mode and supporting guidance. Plugin · github/awesome-copilot
- Search & AI Optimization Expert Expert guidance for modern search optimization: SEO, Answer Engine Optimization (AEO), and Generative Engine Optimization (GEO) with AI-ready content strategies Subagent · github/awesome-copilot
- SE: Tech Writer Technical writing specialist for creating developer documentation, technical blogs, tutorials, and educational content Subagent · github/awesome-copilot
- Senior Cloud Architect Expert in modern architecture design patterns, NFR requirements, and creating comprehensive architectural diagrams and documentation Subagent · github/awesome-copilot
- SE: Security Security-focused code review specialist with OWASP Top 10, Zero Trust, LLM security, and enterprise security standards Subagent · github/awesome-copilot