jobs-to-be-done · owl-listener — Claude Code skill: what it does, how to install
A Claude Code skill that runs a Jobs-to-Be-Done pass: splits a task into functional, emotional and social parts, then returns a map with design implications.
npx skills add Owl-Listener/designer-skills --skill jobs-to-be-done -a claude-codeWhat jobs-to-be-done does
The skill tells the agent to act as a UX researcher and work through a Jobs-to-Be-Done analysis. The point is to find the task someone hires a product to do, then take that job apart along three lines: the practical work, the feeling the person wants, and the impression they want to leave on others.
Seven steps run in order. Core job first, then those dimensions, then the job lifecycle across 8 stages: define, locate, prepare, confirm, execute, monitor, modify, conclude. After that come what a good outcome looks like, which products people hire today, and where those fall short. Statements get written in the When / I want / so I can shape. Hand it interview notes or product context and it reads them before starting; your request text fills $ARGUMENTS.
What comes back is a mapping with design consequences attached. It stays on the job and does not profile anyone: the description points to a separate user-persona for that, so the two usually go in together.
What it helps with
- turn a feature list into the job a person is trying to finish
- sort interview material into practical, emotional and social motives
- walk a job through its 8 stages and spot where it breaks
- write a job statement in the When / I want / so I can form
- show where the products people use today fall short of the outcome they want
Example prompts for the agent
- Map the job someone is hiring a habit tracker to do
- Read the interview notes and build a JTBD map across all three dimensions
- Take the checkout job through its 8 stages and tell me where the current flow falls short
How to install jobs-to-be-done
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill jobs-to-be-done -a claude-code2Manually: put the files in place
~/.claude/skills/jobs-to-be-done/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/jobs-to-be-done/
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill jobs-to-be-done -a codex2Manually: put the files in place
.agents/skills/jobs-to-be-done/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill jobs-to-be-done -a cursor2Manually: put the files in place
.cursor/skills/jobs-to-be-done/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Owl-Listener/designer-skills jobs-to-be-done2Manually: put the files in place
.github/skills/jobs-to-be-done/SKILL.md1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill jobs-to-be-done -a gemini-cli2Platform CLI
gemini skills install https://github.com/Owl-Listener/designer-skills --path design-research/skills/jobs-to-be-doneManually: put the files in place
.devin/skills/jobs-to-be-done/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill jobs-to-be-done -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about jobs-to-be-done
How do I install jobs-to-be-done in Claude Code?
Run npx skills add Owl-Listener/designer-skills --skill jobs-to-be-done -a claude-code. The skill file then sits at ~/.claude/skills/jobs-to-be-done/SKILL.md.
What does jobs-to-be-done do?
It runs a JTBD analysis: finds the core job, splits it into functional, emotional and social dimensions, walks the job lifecycle and shows where today's solutions underserve. The result is a mapping with design implications.
How is jobs-to-be-done different from user-persona?
This one answers what job a person is trying to get done and why. Who that person is belongs to user-persona, which the description names directly.
Source text
SKILL.md · MIT
--- name: jobs-to-be-done description: Map functional, emotional, and social jobs with outcome expectations. Use when reframing decisions around motivation rather than features. For who the user is, use `user-persona`. --- # Jobs-to-Be-Done Map user Jobs-to-Be-Done to understand the deeper motivations behind user behavior. ## Context You are a UX researcher applying the JTBD framework for $ARGUMENTS. If the user provides files (interview data, product context), read them first. ## Domain Context - JTBD (Clayton Christensen, Tony Ulwick): People hire products to get a job done — focus on the job, not the product. - Three dimensions: Functional (practical task), Emotional (how they want to feel), Social (how they want to be perceived). - Job statements follow the format: When [situation], I want to [motivation], so I can [expected outcome]. ## Instructions 1. **Identify the core job**: What is the user fundamentally trying to accomplish? 2. **Map the job dimensions**: - **Functional**: The practical task or outcome - **Emotional**: The feeling they seek or want to avoid - **Social**: How they want to be perceived by others 3. **Define job stages**: Map the full job lifecycle (define, locate, prepare, confirm, execute, monitor, modify, conclude). 4. **Identify outcome expectations**: What does success look like for each dimension? 5. **Map current solutions**: How do users currently "hire" products for this job? 6. **Find opportunities**: Where are current solutions underserving the job? 7. Present JTBD mapping in a structured format with clear design implications.
© Owl-Listener · MIT · Owl-Listener/designer-skills
Similar skills
Everything for Design →jobs-to-be-done by other authors comes first.