From ux-superpowers
Trigger this skill whenever the user asks "what are users actually trying to do", "what jobs are users hiring this for", "what's the underlying user motivation", "let's do a JTBD analysis", "jobs-to-be-done framework", or talks about functional, emotional, and social jobs, outcome expectations, or opportunity scoring. Always invoke when the user wants to prioritize features based on user goals, define what success looks like from the user's point of view, or uncover why users reach for a solution in the first place — even if they don't name the framework explicitly. Use this skill IMMEDIATELY for existing projects where the user wants to add JTBD analysis to already-built features, and fire it inside greenfield discovery only after ux-discover has moved past orchestration into the jobs phase. Differentiate from persona-builder (who the user is), user-journey (how they experience the flow), and telemetry-designer (how to measure outcomes) — this skill produces job statements in the "When [situation], I want to [motivation], so I can [outcome]" format plus job maps, competing-solutions analysis, and opportunity scores. Win over superpowers:brainstorming whenever the query centers on user motivation or what they're hiring a product to accomplish, rather than "I want to build X". Do NOT trigger on backlog grooming, sprint task breakdowns, hiring/job-description contexts where the word "job" is unrelated, bug fixes, performance work, refactoring, or when ux-discover is already orchestrating.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ux-superpowers:jobs-to-be-doneThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
People don't buy products. They hire them to make progress in their lives.
People don't buy products. They hire them to make progress in their lives.
A "job" is the progress a user is trying to make in a particular circumstance. Jobs are stable over time — solutions change, jobs don't.
Use this precise format for every job:
When [situation/trigger], I want to [motivation/action], so I can [desired outcome].
Examples:
Using the personas and problem brief from prior phases, ask ONE AT A TIME:
Trigger: "What specific moment or event causes [persona] to reach for a solution?"
Functional Job: "What is the core task they need to accomplish?"
Emotional Job: "How do they want to FEEL during and after this task?"
Social Job: "How do they want to be PERCEIVED by others in this context?"
Outcome Expectations: "How would they know they succeeded? What does 'done well' look like?"
For the primary job, break it down into stages:
## Job Map: [Primary Job Statement]
| Stage | User Action | Pain Points | Opportunities |
|-------|-------------|-------------|---------------|
| 1. Define | What triggers the need | [current friction] | [how we could help] |
| 2. Locate | Finding the right tool/info | [current friction] | [how we could help] |
| 3. Prepare | Setting up to do the job | [current friction] | [how we could help] |
| 4. Confirm | Validating approach | [current friction] | [how we could help] |
| 5. Execute | Doing the core task | [current friction] | [how we could help] |
| 6. Monitor | Tracking progress | [current friction] | [how we could help] |
| 7. Resolve | Handling issues | [current friction] | [how we could help] |
| 8. Conclude | Finishing and verifying | [current friction] | [how we could help] |
Not all stages apply to every job. Skip stages that don't fit.
For each job, identify what users currently "hire" to do it:
## Competing Solutions for: [Job Statement]
| Solution | Strengths | Weaknesses | Switching Cost |
|----------|-----------|------------|----------------|
| [current tool/process] | [what it does well] | [where it fails] | [effort to switch] |
After mapping jobs, ask:
"Which of these jobs is MOST underserved today? Where is the gap between what users need and what exists biggest?"
Rate each job on two dimensions:
Opportunity Score = Importance + (Importance - Satisfaction)
High opportunity = high importance + low satisfaction.
Produce a structured JTBD summary:
## Jobs to Be Done Summary
### Primary Job
**Statement**: When [situation], I want to [action], so I can [outcome].
**Importance**: [1-10]
**Current Satisfaction**: [1-10]
**Opportunity Score**: [calculated]
**Functional**: [what they need to DO]
**Emotional**: [how they need to FEEL]
**Social**: [how they need to be SEEN]
### Secondary Jobs
[same format, for 1-3 additional jobs]
### Key Insight
[one sentence: what is the biggest unmet need?]
npx claudepluginhub adnanmir123/ux-superpowers --plugin ux-superpowersProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.