Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria. Use when writing user stories, breaking down features into backlog items, or defining acceptance criteria.
.claude/skills/phuryn-user-stories/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-05 | ✓→✗ | ▼ Worse | 63% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | -10% | 0% |
Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria. Generates stories with descriptions, design links, and acceptance criteria.
Use when: Writing user stories, breaking down features into stories, creating backlog items, or defining acceptance criteria.
Arguments:
$PRODUCT: The product or system name$FEATURE: The new feature to break into stories$DESIGN: Link to design files (Figma, Miro, etc.)$ASSUMPTIONS: Key assumptions or contextTitle: Feature name]
Description: As a user role], I want to action], so that benefit].
Design: Link to design files]
Acceptance Criteria:
Title: Recently Viewed Section
Description: As an Online Shopper, I want to see a 'Recently viewed' section on the product page to easily revisit items I considered.
Design: Figma link]
Acceptance Criteria:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 10,021 | 6,903 | -31% | 1 | 1 | 0% | 1,776 | 1,598 | -10% | 0 | 0 | — |
case-01 | fail→pass | 15,296 | 11,443 | -25% | 1 | 1 | 0% | 3,088 | 2,978 | -4% | 0 | 0 | — |
case-02 | fail→pass | 17,770 | 12,902 | -27% | 1 | 1 | 0% | 2,647 | 3,139 | +19% | 0 | 0 | — |
case-03 | pass→pass | 13,141 | 13,152 | +0% | 1 | 1 | 0% | 2,675 | 3,436 | +28% | 0 | 0 | — |
case-04 | pass→pass | 16,268 | 13,821 | -15% | 1 | 1 | 0% | 2,079 | 2,964 | +43% | 0 | 0 | — |
case-05 | pass→fail | 12,364 | 17,700 | +43% | 1 | 1 | 0% | 2,295 | 3,740 | +63% | 0 | 0 | — |
case-07 | pass→pass | 13,595 | 9,531 | -30% | 1 | 1 | 0% | 2,467 | 2,600 | +5% | 0 | 0 | — |
case-08 | pass→pass | 9,645 | 7,708 | -20% | 1 | 1 | 0% | 1,423 | 1,662 | +17% | 0 | 0 | — |
case-09 | pass→pass | 18,714 | 9,906 | -47% | 1 | 1 | 0% | 3,066 | 2,473 | -19% | 0 | 0 | — |
case-10 | fail→pass | 10,502 | 9,343 | -11% | 1 | 1 | 0% | 1,865 | 1,775 | -5% | 0 | 0 | — |
case-11 | pass→pass | 15,259 | 10,753 | -30% | 1 | 1 | 0% | 2,815 | 2,211 | -21% | 0 | 0 | — |
case-12 | pass→pass | 10,681 | 6,229 | -42% | 1 | 1 | 0% | 1,994 | 1,752 | -12% | 0 | 0 | — |
case-13 | pass→pass | 10,318 | 6,719 | -35% | 1 | 1 | 0% | 1,622 | 1,855 | +14% | 0 | 0 | — |
case-14 | pass→pass | 13,031 | 11,455 | -12% | 1 | 1 | 0% | 2,339 | 2,582 | +10% | 0 | 0 | — |
case-15 | pass→pass | 17,865 | 6,441 | -64% | 1 | 1 | 0% | 2,314 | 1,842 | -20% | 0 | 0 | — |
case-16 | pass→pass | 14,925 | 6,195 | -58% | 1 | 1 | 0% | 1,867 | 1,703 | -9% | 0 | 0 | — |
case-17 | pass→pass | 5,921 | 5,613 | -5% | 1 | 1 | 0% | 1,235 | 1,474 | +19% | 0 | 0 | — |
case-18 | pass→pass | 18,219 | 13,778 | -24% | 1 | 1 | 0% | 2,785 | 2,654 | -5% | 0 | 0 | — |
case-19 | pass→pass | 12,694 | 11,241 | -11% | 1 | 1 | 0% | 2,128 | 2,402 | +13% | 0 | 0 | — |
case-20 | pass→pass | 9,901 | 6,418 | -35% | 1 | 1 | 0% | 1,858 | 1,891 | +2% | 0 | 0 | — |
case-21 | pass→pass | 10,462 | 7,145 | -32% | 1 | 1 | 0% | 1,790 | 1,934 | +8% | 0 | 0 | — |
case-22 | pass→pass | 14,306 | 12,206 | -15% | 1 | 1 | 0% | 2,807 | 2,934 | +5% | 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 +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.