Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Insert urgent work as decimal phase (e.g., 72.1) between existing phases
.claude/skills/davepoon-gsd-insert-phase/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-23 | ✗→✓ | ▲ Improved | -65% | 0% |
<objective> Insert a decimal phase for urgent work discovered mid-milestone that must be completed between existing integer phases.
Uses decimal numbering (72.1, 72.2, etc.) to preserve the logical sequence of planned phases while accommodating urgent insertions.
Purpose: Handle urgent work discovered during execution without renumbering entire roadmap. </objective>
<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/insert-phase.md </execution_context>
<context> Arguments: $ARGUMENTS (format: <after-phase-number> <description>)
Roadmap and state are resolved in-workflow via init phase-op and targeted tool calls. </context>
<process> Execute the insert-phase workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/insert-phase.md end-to-end. Preserve all validation gates (argument parsing, phase verification, decimal calculation, roadmap updates). </process>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 2,935 | 5,544 | +89% | 1 | 1 | 0% | 587 | 671 | +14% | 0 | 0 | — |
case-01 | fail→fail | 6,610 | 6,898 | +4% | 1 | 1 | 0% | 1,046 | 586 | -44% | 0 | 0 | — |
case-03 | fail→fail | 4,607 | 6,048 | +31% | 1 | 1 | 0% | 859 | 634 | -26% | 0 | 0 | — |
case-04 | pass→fail | 9,296 | 6,783 | -27% | 1 | 1 | 0% | 1,614 | 896 | -44% | 0 | 0 | — |
case-05 | fail→fail | 4,422 | 11,256 | +155% | 1 | 1 | 0% | 807 | 2,287 | +183% | 0 | 0 | — |
case-06 | pass→pass | 5,314 | 14,668 | +176% | 1 | 1 | 0% | 877 | 3,141 | +258% | 0 | 0 | — |
case-11 | fail→fail | 9,902 | 6,221 | -37% | 1 | 1 | 0% | 1,671 | 646 | -61% | 0 | 0 | — |
case-07 | fail→fail | 8,213 | 8,206 | -0% | 1 | 1 | 0% | 1,505 | 1,632 | +8% | 0 | 0 | — |
case-08 | fail→fail | 7,681 | 7,170 | -7% | 1 | 1 | 0% | 1,307 | 814 | -38% | 0 | 0 | — |
case-09 | fail→pass | 10,630 | 2,977 | -72% | 1 | 1 | 0% | 981 | 686 | -30% | 0 | 0 | — |
case-10 | fail→pass | 8,057 | 2,074 | -74% | 1 | 1 | 0% | 1,285 | 532 | -59% | 0 | 0 | — |
case-12 | fail→fail | 10,550 | 6,553 | -38% | 1 | 1 | 0% | 1,838 | 723 | -61% | 0 | 0 | — |
case-13 | pass→pass | 11,232 | 4,253 | -62% | 1 | 1 | 0% | 2,317 | 947 | -59% | 0 | 0 | — |
case-14 | pass→fail | 8,413 | 5,304 | -37% | 1 | 1 | 0% | 1,582 | 681 | -57% | 0 | 0 | — |
case-15 | fail→pass | 6,033 | 5,104 | -15% | 1 | 1 | 0% | 998 | 1,041 | +4% | 0 | 0 | — |
case-16 | pass→pass | 6,093 | 2,413 | -60% | 1 | 1 | 0% | 1,026 | 572 | -44% | 0 | 0 | — |
case-17 | fail→fail | 10,564 | 5,620 | -47% | 1 | 1 | 0% | 1,992 | 1,204 | -40% | 0 | 0 | — |
case-18 | pass→fail | 7,066 | 5,038 | -29% | 1 | 1 | 0% | 1,157 | 617 | -47% | 0 | 0 | — |
case-19 | pass→pass | 7,108 | 4,608 | -35% | 1 | 1 | 0% | 1,225 | 960 | -22% | 0 | 0 | — |
case-20 | fail→pass | 6,608 | 1,863 | -72% | 1 | 1 | 0% | 1,099 | 490 | -55% | 0 | 0 | — |
case-21 | fail→fail | 12,740 | 7,179 | -44% | 1 | 1 | 0% | 2,052 | 1,497 | -27% | 0 | 0 | — |
case-22 | pass→pass | 7,989 | 3,667 | -54% | 1 | 1 | 0% | 1,454 | 833 | -43% | 0 | 0 | — |
case-23 | fail→pass | 10,854 | 2,604 | -76% | 1 | 1 | 0% | 1,885 | 667 | -65% | 0 | 0 | — |
case-24 | pass→pass | 10,211 | 4,761 | -53% | 1 | 1 | 0% | 1,640 | 981 | -40% | 0 | 0 | — |
case-25 | pass→pass | 12,394 | 8,226 | -34% | 1 | 1 | 0% | 1,945 | 1,727 | -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. 25 cases were attempted, and 16 counted toward the lift figure. The other 9 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 +8 percentage points is the difference between those two pass rates over the 16 comparable cases. 6 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.