Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Gated PRD generation — interrogates problem, user, and metric before drafting; refuses to draft on unknowns. Usage: /prd <feature-or-problem>
.claude/skills/alirezarezvani-prd/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -24% | 0% |
Generate a concise, evidence-gated product requirements document for $ARGUMENTS.
bash/prd <feature-or-problem>
$ARGUMENTS is the feature, initiative, or problem statement. If empty, ask for it before doing anything else.
Walk these one at a time. Do not batch them. Each answer feeds a required PRD section.
Refuse to draft the PRD if the answer to question 1 (problem), 2 (user), or 3 (metric) is unknown, circular, or "we'll figure it out later." Instead, output the open questions and the cheapest way to answer each (e.g., 5 customer interviews, a funnel query, a fake-door test). A PRD without a problem, a user, and a metric is a feature wish, not a requirements document.
Every PRD must contain all of these sections — emit the checklist at the end and mark each:
Keep it to ~2 pages. Use the repo template as the skeleton.
If the user has multiple candidate features, offer to RICE-score them before committing the PRD:
bashpython3 product-team/skills/product-manager-toolkit/scripts/rice_prioritizer.py features.csv --capacity 20
product-team/skills/product-manager-toolkit/SKILL.mdproduct-team/skills/product-manager-toolkit/assets/prd_template.mdproduct-team/skills/product-manager-toolkit/references/prd_templates.mdproduct-team/skills/product-manager-toolkit/scripts/rice_prioritizer.py/code-to-prd — reverse-engineer a PRD from an existing codebase/rice — standalone RICE prioritization| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 11,320 | 6,182 | -45% | 1 | 1 | 0% | 2,101 | 1,965 | -6% | 0 | 0 | — |
case-01 | fail→pass | 6,849 | 2,211 | -68% | 1 | 1 | 0% | 1,245 | 1,136 | -9% | 0 | 0 | — |
case-02 | fail→pass | 12,106 | 2,084 | -83% | 1 | 1 | 0% | 2,157 | 1,091 | -49% | 0 | 0 | — |
case-03 | fail→pass | 15,287 | 2,539 | -83% | 1 | 1 | 0% | 2,934 | 1,215 | -59% | 0 | 0 | — |
case-04 | fail→pass | 11,935 | 5,346 | -55% | 1 | 1 | 0% | 2,220 | 1,688 | -24% | 0 | 0 | — |
case-05 | fail→pass | 14,403 | 5,000 | -65% | 1 | 1 | 0% | 2,595 | 1,704 | -34% | 0 | 0 | — |
case-07 | fail→pass | 9,152 | 2,041 | -78% | 1 | 1 | 0% | 1,531 | 1,051 | -31% | 0 | 0 | — |
case-08 | fail→pass | 7,945 | 4,295 | -46% | 1 | 1 | 0% | 1,383 | 1,495 | +8% | 0 | 0 | — |
case-09 | fail→fail | 8,039 | 6,202 | -23% | 1 | 1 | 0% | 1,378 | 1,908 | +38% | 0 | 0 | — |
case-10 | fail→pass | 7,259 | 3,038 | -58% | 1 | 1 | 0% | 1,258 | 1,349 | +7% | 0 | 0 | — |
case-11 | fail→pass | 27,704 | 11,887 | -57% | 1 | 1 | 0% | 5,009 | 3,105 | -38% | 0 | 0 | — |
case-12 | pass→pass | 15,621 | 9,928 | -36% | 1 | 1 | 0% | 2,507 | 2,452 | -2% | 0 | 0 | — |
case-13 | pass→pass | 12,173 | 5,739 | -53% | 1 | 1 | 0% | 2,172 | 1,681 | -23% | 0 | 0 | — |
case-14 | pass→pass | 5,040 | 1,434 | -72% | 1 | 1 | 0% | 844 | 898 | +6% | 0 | 0 | — |
case-15 | pass→fail | 10,635 | 6,205 | -42% | 1 | 1 | 0% | 1,862 | 1,877 | +1% | 0 | 0 | — |
case-16 | fail→pass | 29,910 | 4,239 | -86% | 1 | 1 | 0% | 6,170 | 1,433 | -77% | 0 | 0 | — |
case-17 | fail→pass | 9,246 | 5,976 | -35% | 1 | 1 | 0% | 1,738 | 1,813 | +4% | 0 | 0 | — |
case-18 | fail→pass | 15,064 | 4,228 | -72% | 1 | 1 | 0% | 2,495 | 1,381 | -45% | 0 | 0 | — |
case-19 | fail→pass | 5,263 | 1,620 | -69% | 1 | 1 | 0% | 971 | 1,031 | +6% | 0 | 0 | — |
case-20 | pass→pass | 3,692 | 4,053 | +10% | 1 | 1 | 0% | 719 | 1,462 | +103% | 0 | 0 | — |
case-21 | pass→pass | 17,627 | 21,320 | +21% | 1 | 1 | 0% | 3,808 | 5,172 | +36% | 0 | 0 | — |
case-22 | pass→pass | 9,225 | 15,762 | +71% | 1 | 1 | 0% | 1,661 | 3,742 | +125% | 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 +59 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.