Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interactive command center for managing multiple phases from one terminal
.claude/skills/davepoon-gsd-manager/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -53% | 0% |
<objective> Single-terminal command center for managing a milestone. Shows a dashboard of all phases with visual status indicators, recommends optimal next actions, and dispatches work — discuss runs inline, plan/execute run as background agents.
Designed for power users who want to parallelize work across phases from one terminal: discuss a phase while another plans or executes in the background.
Creates/Updates:
.planning/STATE.md, .planning/ROADMAP.md, phase directories for status.After: User exits when done managing, or all phases complete and milestone lifecycle is suggested. </objective>
<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/manager.md @${CLAUDE_PLUGIN_ROOT}/references/ui-brand.md </execution_context>
<context> No arguments required. Requires an active milestone with ROADMAP.md and STATE.md.
Project context, phase list, dependencies, and recommendations are resolved inside the workflow using gsd-sdk query init.manager. No upfront context loading needed. </context>
<process> Execute the manager workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/manager.md end-to-end. Maintain the dashboard refresh loop until the user exits or all phases complete. </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 | 14,647 | 3,865 | -74% | 1 | 1 | 0% | 3,295 | 524 | -84% | 0 | 0 | — |
case-02 | fail→fail | 8,098 | 5,411 | -33% | 1 | 1 | 0% | 1,196 | 718 | -40% | 0 | 0 | — |
case-03 | fail→fail | 3,400 | 6,001 | +77% | 1 | 1 | 0% | 243 | 551 | +127% | 0 | 0 | — |
case-04 | fail→pass | 13,541 | 4,675 | -65% | 1 | 1 | 0% | 2,275 | 1,126 | -51% | 0 | 0 | — |
case-05 | fail→fail | 10,839 | 3,164 | -71% | 1 | 1 | 0% | 1,713 | 813 | -53% | 0 | 0 | — |
case-06 | fail→pass | 11,602 | 6,438 | -45% | 1 | 1 | 0% | 1,979 | 1,359 | -31% | 0 | 0 | — |
case-07 | fail→pass | 7,823 | 2,775 | -65% | 1 | 1 | 0% | 1,294 | 721 | -44% | 0 | 0 | — |
case-08 | fail→pass | 9,054 | 3,801 | -58% | 1 | 1 | 0% | 1,454 | 1,009 | -31% | 0 | 0 | — |
case-09 | fail→pass | 7,374 | 1,728 | -77% | 1 | 1 | 0% | 1,288 | 610 | -53% | 0 | 0 | — |
case-10 | fail→pass | 7,825 | 1,708 | -78% | 1 | 1 | 0% | 1,308 | 562 | -57% | 0 | 0 | — |
case-11 | fail→pass | 8,150 | 1,298 | -84% | 1 | 1 | 0% | 1,411 | 493 | -65% | 0 | 0 | — |
case-12 | fail→pass | 10,676 | 2,145 | -80% | 1 | 1 | 0% | 1,873 | 658 | -65% | 0 | 0 | — |
case-13 | pass→pass | 10,523 | 2,311 | -78% | 1 | 1 | 0% | 1,709 | 631 | -63% | 0 | 0 | — |
case-14 | pass→pass | 7,838 | 2,015 | -74% | 1 | 1 | 0% | 1,266 | 542 | -57% | 0 | 0 | — |
case-15 | fail→pass | 12,381 | 4,366 | -65% | 1 | 1 | 0% | 1,911 | 1,051 | -45% | 0 | 0 | — |
case-16 | fail→pass | 13,670 | 3,117 | -77% | 1 | 1 | 0% | 2,499 | 781 | -69% | 0 | 0 | — |
case-17 | fail→pass | 14,486 | 6,417 | -56% | 1 | 1 | 0% | 2,501 | 1,328 | -47% | 0 | 0 | — |
case-18 | fail→pass | 9,853 | 2,142 | -78% | 1 | 1 | 0% | 1,476 | 581 | -61% | 0 | 0 | — |
case-19 | fail→pass | 12,410 | 6,257 | -50% | 1 | 1 | 0% | 1,988 | 1,316 | -34% | 0 | 0 | — |
case-20 | pass→pass | 10,840 | 6,629 | -39% | 1 | 1 | 0% | 1,915 | 1,480 | -23% | 0 | 0 | — |
case-21 | pass→fail | 11,532 | 14,067 | +22% | 1 | 1 | 0% | 2,022 | 1,697 | -16% | 0 | 0 | — |
case-22 | pass→pass | 8,089 | 9,370 | +16% | 1 | 1 | 0% | 1,701 | 2,012 | +18% | 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 18 counted toward the lift figure. The other 4 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 +55 percentage points is the difference between those two pass rates over the 18 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.