Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Start a new milestone cycle — update PROJECT.md and route to requirements
.claude/skills/davepoon-gsd-new-milestone/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -33% | 0% |
<objective> Start a new milestone: questioning → research (optional) → requirements → roadmap.
Brownfield equivalent of new-project. Project exists, PROJECT.md has history. Gathers "what's next", updates PROJECT.md, then runs requirements → roadmap cycle.
Creates/Updates:
.planning/PROJECT.md — updated with new milestone goals.planning/research/ — domain research (optional, NEW features only).planning/REQUIREMENTS.md — scoped requirements for this milestone.planning/ROADMAP.md — phase structure (continues numbering).planning/STATE.md — reset for new milestoneAfter: /gsd:plan-phase [N] to start execution. </objective>
<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/new-milestone.md @${CLAUDE_PLUGIN_ROOT}/references/questioning.md @${CLAUDE_PLUGIN_ROOT}/references/ui-brand.md @${CLAUDE_PLUGIN_ROOT}/templates/project.md @${CLAUDE_PLUGIN_ROOT}/templates/requirements.md </execution_context>
<context> Milestone name: $ARGUMENTS (optional - will prompt if not provided)
Project and milestone context files are resolved inside the workflow (init new-milestone) and delegated via <files_to_read> blocks where subagents are used. </context>
<process> Execute the new-milestone workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/new-milestone.md end-to-end. Preserve all workflow gates (validation, questioning, research, requirements, roadmap approval, commits). </process>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 8,326 | 5,448 | -35% | 1 | 1 | 0% | 1,388 | 693 | -50% | 0 | 0 | — |
case-02 | fail→fail | 11,615 | 4,496 | -61% | 1 | 1 | 0% | 2,188 | 577 | -74% | 0 | 0 | — |
case-03 | fail→fail | 10,084 | 4,400 | -56% | 1 | 1 | 0% | 1,871 | 660 | -65% | 0 | 0 | — |
case-04 | pass→pass | 6,772 | 2,638 | -61% | 1 | 1 | 0% | 1,219 | 819 | -33% | 0 | 0 | — |
case-05 | fail→fail | 9,324 | 20,750 | +123% | 1 | 1 | 0% | 2,063 | 4,028 | +95% | 0 | 0 | — |
case-06 | fail→fail | 1,675 | 8,934 | +433% | 1 | 1 | 0% | 239 | 955 | +300% | 0 | 0 | — |
case-07 | pass→pass | 8,489 | 4,463 | -47% | 1 | 1 | 0% | 1,501 | 1,195 | -20% | 0 | 0 | — |
case-08 | pass→pass | 5,375 | 3,693 | -31% | 1 | 1 | 0% | 903 | 986 | +9% | 0 | 0 | — |
case-09 | pass→pass | 8,977 | 3,458 | -61% | 1 | 1 | 0% | 1,416 | 997 | -30% | 0 | 0 | — |
case-10 | pass→pass | 6,472 | 1,867 | -71% | 1 | 1 | 0% | 1,131 | 678 | -40% | 0 | 0 | — |
case-11 | fail→pass | 10,447 | 3,667 | -65% | 1 | 1 | 0% | 1,735 | 900 | -48% | 0 | 0 | — |
case-12 | pass→pass | 11,754 | 4,655 | -60% | 1 | 1 | 0% | 2,063 | 1,209 | -41% | 0 | 0 | — |
case-13 | pass→pass | 2,659 | 2,117 | -20% | 1 | 1 | 0% | 418 | 720 | +72% | 0 | 0 | — |
case-14 | pass→pass | 9,241 | 3,340 | -64% | 1 | 1 | 0% | 1,741 | 980 | -44% | 0 | 0 | — |
case-15 | fail→pass | 9,505 | 3,652 | -62% | 1 | 1 | 0% | 1,618 | 1,006 | -38% | 0 | 0 | — |
case-16 | fail→pass | 11,024 | 3,423 | -69% | 1 | 1 | 0% | 1,895 | 959 | -49% | 0 | 0 | — |
case-17 | pass→pass | 9,589 | 4,248 | -56% | 1 | 1 | 0% | 1,612 | 1,111 | -31% | 0 | 0 | — |
case-18 | pass→pass | 8,847 | 2,554 | -71% | 1 | 1 | 0% | 1,462 | 792 | -46% | 0 | 0 | — |
case-19 | fail→pass | 11,392 | 4,608 | -60% | 1 | 1 | 0% | 1,929 | 1,248 | -35% | 0 | 0 | — |
case-20 | pass→pass | 5,417 | 2,692 | -50% | 1 | 1 | 0% | 848 | 809 | -5% | 0 | 0 | — |
case-21 | fail→fail | 11,510 | 5,016 | -56% | 1 | 1 | 0% | 1,933 | 970 | -50% | 0 | 0 | — |
case-22 | pass→pass | 8,179 | 1,430 | -83% | 1 | 1 | 0% | 1,328 | 654 | -51% | 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, and 17 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +18 percentage points is the difference between those two pass rates over the 17 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.