Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Jobs-to-Be-Done story writing that focuses on user situations and motivations rather than personas. Use to write When/Want/So backlog items, run a JTBD discovery canvas, apply INVEST, and convert user stories to job stories.
.claude/skills/borghei-job-stories/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 189% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 424% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 60% | 0% |
Write job stories using the Jobs-to-Be-Done (JTBD) framework. Unlike traditional user stories that focus on roles ("As a user..."), job stories focus on the situation, motivation, and desired outcome. This shift produces requirements that are more grounded in real user context and less likely to encode assumptions about who the user is.
The format is When [situation], I want to [motivation], so I can [outcome]. Removing the role and describing the situation matters because the same person has different needs in different situations, different people in the same situation share needs, and situations are observable and testable while roles are abstract labels.
wwas/ instead.Before writing job stories, confirm these inputs. If any is unknown or vague, ASK — do not assume:
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.
When [situation], I want to [motivation], so I can [outcome].Load the reference that matches the task — keep this file lean and pull detail on demand:
In Scope: Writing job stories using JTBD "When/Want/So" format, applying INVEST quality criteria, writing outcome-focused acceptance criteria, converting existing user stories to job stories, facilitating story-writing workshops, integrating job stories with Jira backlog items.
Out of Scope: Strategic backlog items with business context (hand off to wwas/), product ideation and opportunity discovery (hand off to discovery/brainstorm-ideas/), detailed technical specifications, UX research and user interviewing methodology.
Limitations: Job stories work best when the team has access to real user research (interviews, observation, support data). Without user context, teams will invent situations that may not reflect reality. The format is less natural for purely technical or infrastructure work where there is no direct user situation. Job stories and user stories are complementary -- some teams use both formats for different types of work.
| Integration | Direction | What Flows | |-------------|-----------|------------| | wwas/ | Complementary | WWAS adds strategic "Why" context; job stories add situational "When" context. Use both when needed | | summarize-meeting/ | Meetings -> Stories | Discovery conversations and refinement sessions produce the situations that inform job stories | | ../jira-expert/ | Stories -> Jira | Completed job stories become Jira tickets with structured descriptions | | discovery/brainstorm-ideas/ | Ideas -> Stories | Validated product ideas decompose into job stories for the backlog | | execution/brainstorm-okrs/ | OKRs -> Stories | Team objectives define the outcomes that job stories should connect to | | execution/prioritization-frameworks/ | Stories -> Prioritization | Job stories scored via RICE or other frameworks for sprint planning |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,764 | 10,407 | -12% | 1 | 1 | 0% | 1,780 | 2,847 | +60% | 0 | 0 | — |
case-02 | fail→pass | 8,567 | 14,267 | +67% | 1 | 1 | 0% | 1,227 | 3,547 | +189% | 0 | 0 | — |
case-03 | pass→pass | 11,598 | 10,221 | -12% | 1 | 1 | 0% | 1,908 | 2,934 | +54% | 0 | 0 | — |
case-04 | fail→pass | 4,626 | 14,407 | +211% | 1 | 1 | 0% | 692 | 3,624 | +424% | 0 | 0 | — |
case-05 | pass→pass | 6,199 | 12,668 | +104% | 1 | 1 | 0% | 928 | 3,323 | +258% | 0 | 0 | — |
case-06 | pass→pass | 7,362 | 12,628 | +72% | 1 | 1 | 0% | 1,188 | 3,248 | +173% | 0 | 0 | — |
case-07 | pass→pass | 8,561 | 8,479 | -1% | 1 | 1 | 0% | 1,286 | 2,519 | +96% | 0 | 0 | — |
case-08 | fail→pass | 17,292 | 6,361 | -63% | 1 | 1 | 0% | 2,654 | 2,286 | -14% | 0 | 0 | — |
case-09 | fail→fail | 26,379 | 25,907 | -2% | 1 | 1 | 0% | 4,077 | 5,309 | +30% | 0 | 0 | — |
case-10 | fail→pass | 23,731 | 22,117 | -7% | 1 | 1 | 0% | 3,510 | 4,532 | +29% | 0 | 0 | — |
case-11 | fail→pass | 9,156 | 7,124 | -22% | 1 | 1 | 0% | 1,430 | 2,293 | +60% | 0 | 0 | — |
case-12 | pass→pass | 6,751 | 9,759 | +45% | 1 | 1 | 0% | 1,156 | 2,805 | +143% | 0 | 0 | — |
case-13 | pass→pass | 10,619 | 14,885 | +40% | 1 | 1 | 0% | 1,766 | 3,753 | +113% | 0 | 0 | — |
case-14 | fail→fail | 7,950 | 14,505 | +82% | 1 | 1 | 0% | 1,184 | 3,542 | +199% | 0 | 0 | — |
case-15 | fail→fail | 12,586 | 10,805 | -14% | 1 | 1 | 0% | 2,276 | 3,100 | +36% | 0 | 0 | — |
case-16 | pass→pass | 10,488 | 13,921 | +33% | 1 | 1 | 0% | 1,607 | 3,451 | +115% | 0 | 0 | — |
case-17 | pass→pass | 12,803 | 14,998 | +17% | 1 | 1 | 0% | 2,007 | 3,698 | +84% | 0 | 0 | — |
case-18 | pass→pass | 13,598 | 10,091 | -26% | 1 | 1 | 0% | 2,130 | 2,915 | +37% | 0 | 0 | — |
case-19 | pass→pass | 16,507 | 10,440 | -37% | 1 | 1 | 0% | 2,592 | 2,922 | +13% | 0 | 0 | — |
case-20 | pass→pass | 15,580 | 13,107 | -16% | 1 | 1 | 0% | 2,381 | 3,394 | +43% | 0 | 0 | — |
case-21 | pass→pass | 18,518 | 15,320 | -17% | 1 | 1 | 0% | 2,738 | 3,621 | +32% | 0 | 0 | — |
case-22 | fail→fail | 10,824 | 15,928 | +47% | 1 | 1 | 0% | 1,641 | 3,707 | +126% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +23 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.