
Job Stories Writer
Writes user stories in the 'When..., I want to..., so I can...' format with acceptance criteria
- Repository
- phuryn/pm-skills
- Stars
- 27,616
- Licence
- MIT
- Files
- 1 file
What it does
This skill teaches an AI agent to write product backlog items as job stories, a way of describing what a user is trying to get done in a given situation rather than who they are. Each story follows the pattern 'When [situation], I want to [motivation], so I can [outcome]', followed by acceptance criteria that describe how to tell the outcome was achieved. It also reminds the agent to link to design files if they are provided.
Great for
- Product managers writing backlog items for a new feature
- Teams that use Jobs-to-be-Done (JTBD) thinking and want consistent story wording
- Anyone who wants a worked example of a job story with measurable acceptance criteria
Skip it if
- Teams that need strict role-based user stories ('As a user...') because their tooling or process requires that format
- Situations needing verified market research or real customer data, since the skill only shapes wording and structure from what the user supplies
- Safety-critical or compliance requirements, which need expert review beyond what a template-style output can provide
Try asking
- “Write job stories for a new expense-tracking feature in our budgeting app”
- “Turn these customer interview notes into JTBD-style backlog items with acceptance criteria”
- “Create a set of job stories for onboarding a new user to our project tool, linking our Figma file”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
job-stories.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip job-stories.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip job-stories.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide concrete user situations in the context argument so stories reflect real scenarios rather than generic ones.
- Review the generated acceptance criteria against your own definition of done, since they are drafted from wording alone.
- Include the product name and design link when available so the output is tied to your actual feature.
What's inside
- SKILL.md
Redistributed unmodified from phuryn/pm-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.