Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Add an idea to the backlog parking lot (999.x numbering)
.claude/skills/coco-research-gsd-add-backlog/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -13% | 0% |
<objective> Add a backlog item to the roadmap using 999.x numbering. Backlog items are unsequenced ideas that aren't ready for active planning — they live outside the normal phase sequence and accumulate context over time. </objective>
<process>
bash cat .planning/ROADMAP.md
bash NEXT=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" phase next-decimal 999 --raw) If no 999.x phases exist, start at 999.1.
bash SLUG=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" generate-slug "$ARGUMENTS" --raw) mkdir -p ".planning/phases/${NEXT}-${SLUG}" touch ".planning/phases/${NEXT}-${SLUG}/.gitkeep"
## Backlog section. If the section doesn't exist, create it at the end:markdown ## Backlog
### Phase {NEXT}: {description} (BACKLOG)
Goal: Captured for future planning] Requirements: TBD Plans: 0 plans
Plans:
bash node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" commit "docs: add backlog item ${NEXT} — ${ARGUMENTS}" --files .planning/ROADMAP.md ".planning/phases/${NEXT}-${SLUG}/.gitkeep"
## 📋 Backlog Item Added
Phase {NEXT}: {description} Directory: .planning/phases/{NEXT}-{slug}/
This item lives in the backlog parking lot. Use /gsd-discuss-phase {NEXT} to explore it further. Use /gsd-review-backlog to promote items to active milestone.
</process>
<notes>
Depends on: field — backlog items are unsequenced by definition</notes>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 15,079 | 15,312 | +2% | 1 | 1 | 0% | 1,414 | 912 | -36% | 0 | 0 | — |
case-02 | fail→fail | 9,996 | 9,335 | -7% | 1 | 1 | 0% | 217 | 856 | +294% | 0 | 0 | — |
case-03 | fail→fail | 3,961 | 10,393 | +162% | 1 | 1 | 0% | 624 | 774 | +24% | 0 | 0 | — |
case-04 | fail→fail | 11,557 | 10,830 | -6% | 1 | 1 | 0% | 1,099 | 860 | -22% | 0 | 0 | — |
case-05 | fail→fail | 19,185 | 9,075 | -53% | 1 | 1 | 0% | 1,093 | 759 | -31% | 0 | 0 | — |
case-06 | fail→pass | 21,742 | 7,766 | -64% | 1 | 1 | 0% | 2,906 | 1,164 | -60% | 0 | 0 | — |
case-07 | fail→pass | 11,756 | 9,672 | -18% | 1 | 1 | 0% | 1,531 | 1,553 | +1% | 0 | 0 | — |
case-08 | fail→fail | 16,677 | 13,613 | -18% | 1 | 1 | 0% | 1,830 | 1,041 | -43% | 0 | 0 | — |
case-09 | fail→pass | 11,742 | 2,697 | -77% | 1 | 1 | 0% | 1,758 | 964 | -45% | 0 | 0 | — |
case-10 | pass→pass | 8,772 | 2,068 | -76% | 1 | 1 | 0% | 1,235 | 955 | -23% | 0 | 0 | — |
case-11 | fail→pass | 11,731 | 1,727 | -85% | 1 | 1 | 0% | 1,799 | 926 | -49% | 0 | 0 | — |
case-12 | fail→fail | 13,455 | 7,113 | -47% | 1 | 1 | 0% | 1,197 | 900 | -25% | 0 | 0 | — |
case-13 | pass→pass | 11,068 | 6,338 | -43% | 1 | 1 | 0% | 1,060 | 819 | -23% | 0 | 0 | — |
case-14 | fail→fail | 9,581 | 1,348 | -86% | 1 | 1 | 0% | 1,241 | 822 | -34% | 0 | 0 | — |
case-15 | fail→pass | 7,486 | 2,622 | -65% | 1 | 1 | 0% | 1,108 | 969 | -13% | 0 | 0 | — |
case-16 | pass→fail | 8,774 | 2,179 | -75% | 1 | 1 | 0% | 614 | 1,010 | +64% | 0 | 0 | — |
case-17 | fail→pass | 19,621 | 7,854 | -60% | 1 | 1 | 0% | 2,197 | 1,008 | -54% | 0 | 0 | — |
case-18 | fail→pass | 10,782 | 1,688 | -84% | 1 | 1 | 0% | 1,545 | 811 | -48% | 0 | 0 | — |
case-19 | fail→pass | 12,733 | 6,881 | -46% | 1 | 1 | 0% | 1,353 | 898 | -34% | 0 | 0 | — |
case-20 | fail→fail | 15,490 | 10,640 | -31% | 1 | 1 | 0% | 261 | 893 | +242% | 0 | 0 | — |
case-21 | pass→fail | 23,144 | 15,480 | -33% | 1 | 1 | 0% | 4,027 | 1,061 | -74% | 0 | 0 | — |
case-22 | pass→fail | 12,181 | 10,533 | -14% | 1 | 1 | 0% | 1,111 | 941 | -15% | 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 13 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 +23 percentage points is the difference between those two pass rates over the 13 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.