Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Creates clear, testable specifications from feature descriptions with user stories. Use when starting a new feature and needing a spec before planning.
.claude/skills/athola-spec-writing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 13% | 0% |
Create clear, complete, and testable specifications from natural language feature descriptions. Specifications focus on user value and business needs, avoiding implementation details.
Focus on user value and business needs rather than implementation details. Avoid specifying technology choices in requirement definitions unless strictly necessary. Ensure every requirement is testable and verifiable with measurable criteria. Limit clarification markers; make informed assumptions based on industry standards and document them explicitly.
See: modules/specification-structure.md for detailed templates and guidelines
See: modules/success-criteria-patterns.md for detailed examples and conversion process
speckit-orchestrator: Workflow coordinationtask-planning: Converting specs to tasksIf specifications are too vague, use the success-criteria-patterns module to enforce measurable outcomes. If implementation details leak into specs, review against the "Core Principles" and refactor to focus on user behavior.
User Scenarios, Functional Requirements, and Success Criteria
complete checkout in under 3 minutes") not implementation metrics (e.g. "API response under 200ms")
requirements unambiguous, edge cases identified, scope bounded
explicitly marks them as strictly necessary constraints
criterion that can be verified from outside the system
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 13,621 | 32,398 | +138% | 1 | 1 | 0% | 2,289 | 3,124 | +36% | 0 | 0 | — |
case-13 | fail→fail | 22,019 | 18,339 | -17% | 1 | 1 | 0% | 3,809 | 3,935 | +3% | 0 | 0 | — |
case-19 | pass→pass | 16,196 | 16,400 | +1% | 1 | 1 | 0% | 2,825 | 3,273 | +16% | 0 | 0 | — |
case-01 | fail→pass | 23,573 | 16,518 | -30% | 1 | 1 | 0% | 3,789 | 3,408 | -10% | 0 | 0 | — |
case-02 | fail→pass | 24,323 | 15,945 | -34% | 1 | 1 | 0% | 3,759 | 3,101 | -18% | 0 | 0 | — |
case-03 | pass→fail | 16,588 | 3,567 | -78% | 1 | 1 | 0% | 2,828 | 1,179 | -58% | 0 | 0 | — |
case-04 | pass→fail | 25,001 | 14,504 | -42% | 1 | 1 | 0% | 4,175 | 3,057 | -27% | 0 | 0 | — |
case-05 | pass→fail | 18,664 | 22,302 | +19% | 1 | 1 | 0% | 3,264 | 4,242 | +30% | 0 | 0 | — |
case-06 | fail→fail | 17,708 | 25,506 | +44% | 1 | 1 | 0% | 3,068 | 3,303 | +8% | 0 | 0 | — |
case-07 | fail→pass | 19,192 | 12,317 | -36% | 1 | 1 | 0% | 3,046 | 2,642 | -13% | 0 | 0 | — |
case-08 | fail→fail | 30,788 | 15,897 | -48% | 1 | 1 | 0% | 3,239 | 3,115 | -4% | 0 | 0 | — |
case-09 | pass→pass | 22,589 | 17,801 | -21% | 1 | 1 | 0% | 3,448 | 3,524 | +2% | 0 | 0 | — |
case-10 | fail→pass | 15,894 | 15,024 | -5% | 1 | 1 | 0% | 2,433 | 2,953 | +21% | 0 | 0 | — |
case-11 | fail→pass | 20,682 | 34,332 | +66% | 1 | 1 | 0% | 3,213 | 3,626 | +13% | 0 | 0 | — |
case-14 | pass→pass | 35,612 | 16,676 | -53% | 1 | 1 | 0% | 3,126 | 3,379 | +8% | 0 | 0 | — |
case-15 | fail→pass | 18,649 | 14,880 | -20% | 1 | 1 | 0% | 3,150 | 3,130 | -1% | 0 | 0 | — |
case-16 | pass→pass | 16,416 | 15,743 | -4% | 1 | 1 | 0% | 2,761 | 3,276 | +19% | 0 | 0 | — |
case-17 | pass→pass | 25,127 | 16,157 | -36% | 1 | 1 | 0% | 3,831 | 3,195 | -17% | 0 | 0 | — |
case-18 | pass→pass | 22,885 | 15,423 | -33% | 1 | 1 | 0% | 3,564 | 3,064 | -14% | 0 | 0 | — |
case-20 | fail→fail | 22,530 | 15,129 | -33% | 1 | 1 | 0% | 3,687 | 2,922 | -21% | 0 | 0 | — |
case-21 | fail→fail | 18,016 | 14,611 | -19% | 1 | 1 | 0% | 2,946 | 3,174 | +8% | 0 | 0 | — |
case-22 | fail→pass | 21,451 | 20,206 | -6% | 1 | 1 | 0% | 3,521 | 3,139 | -11% | 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 +18 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.