Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate user stories with acceptance criteria and sprint planning. Usage: /user-story <generate|sprint> [options]
.claude/skills/alirezarezvani-user-story/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 104% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -64% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -65% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -36% | 0% |
Generate structured user stories with acceptance criteria, story points, and sprint capacity planning.
/user-story generate Generate user stories (interactive)
/user-story sprint <capacity> Plan sprint with story point capacityInteractive mode prompts for feature context. For sprint planning, provide capacity as story points:
/user-story generate
> Feature: User authentication
> Persona: Engineering manager
> Epic: Platform Security
/user-story sprint 21
> Stories are ranked by priority and fit within 21-point capacity/user-story generate
/user-story sprint 34
/user-story sprint 21product-team/agile-product-owner/skills/agile-product-owner/scripts/user_story_generator.py — User story generator (positional args: sprint <capacity>)> product-team/agile-product-owner/skills/agile-product-owner/SKILL.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,342 | 15,198 | +107% | 1 | 1 | 0% | 1,340 | 2,732 | +104% | 0 | 0 | — |
case-02 | pass→pass | 10,228 | 13,928 | +36% | 1 | 1 | 0% | 1,744 | 1,394 | -20% | 0 | 0 | — |
case-03 | pass→pass | 33,082 | 18,213 | -45% | 1 | 1 | 0% | 5,644 | 3,408 | -40% | 0 | 0 | — |
case-04 | pass→pass | 14,214 | 11,281 | -21% | 1 | 1 | 0% | 2,586 | 2,058 | -20% | 0 | 0 | — |
case-05 | fail→pass | 8,247 | 1,427 | -83% | 1 | 1 | 0% | 1,263 | 451 | -64% | 0 | 0 | — |
case-06 | fail→pass | 7,920 | 1,637 | -79% | 1 | 1 | 0% | 1,193 | 462 | -61% | 0 | 0 | — |
case-07 | fail→pass | 8,978 | 1,373 | -85% | 1 | 1 | 0% | 1,284 | 453 | -65% | 0 | 0 | — |
case-08 | fail→pass | 9,017 | 4,511 | -50% | 1 | 1 | 0% | 1,580 | 1,011 | -36% | 0 | 0 | — |
case-09 | fail→pass | 8,306 | 1,445 | -83% | 1 | 1 | 0% | 1,613 | 485 | -70% | 0 | 0 | — |
case-10 | pass→pass | 8,267 | 1,754 | -79% | 1 | 1 | 0% | 1,481 | 608 | -59% | 0 | 0 | — |
case-11 | fail→pass | 7,012 | 1,559 | -78% | 1 | 1 | 0% | 1,161 | 466 | -60% | 0 | 0 | — |
case-12 | fail→pass | 11,307 | 7,193 | -36% | 1 | 1 | 0% | 1,951 | 1,378 | -29% | 0 | 0 | — |
case-13 | pass→pass | 11,824 | 10,030 | -15% | 1 | 1 | 0% | 2,281 | 1,549 | -32% | 0 | 0 | — |
case-14 | pass→pass | 6,074 | 4,978 | -18% | 1 | 1 | 0% | 936 | 1,064 | +14% | 0 | 0 | — |
case-15 | fail→pass | 7,413 | 3,103 | -58% | 1 | 1 | 0% | 1,134 | 695 | -39% | 0 | 0 | — |
case-16 | fail→fail | 4,236 | 1,839 | -57% | 1 | 1 | 0% | 709 | 527 | -26% | 0 | 0 | — |
case-17 | pass→pass | 7,642 | 6,737 | -12% | 1 | 1 | 0% | 1,365 | 1,499 | +10% | 0 | 0 | — |
case-18 | pass→pass | 11,287 | 8,984 | -20% | 1 | 1 | 0% | 1,930 | 1,842 | -5% | 0 | 0 | — |
case-19 | pass→pass | 9,560 | 6,452 | -33% | 1 | 1 | 0% | 1,555 | 1,505 | -3% | 0 | 0 | — |
case-20 | fail→pass | 15,005 | 12,386 | -17% | 1 | 1 | 0% | 2,589 | 2,681 | +4% | 0 | 0 | — |
case-21 | fail→pass | 11,290 | 4,643 | -59% | 1 | 1 | 0% | 2,119 | 1,067 | -50% | 0 | 0 | — |
case-22 | pass→pass | 6,095 | 2,216 | -64% | 1 | 1 | 0% | 958 | 518 | -46% | 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 +50 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.