Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create PR, run review, and prepare for merge after verification passes
.claude/skills/coco-research-gsd-ship/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 689% | 0% |
| case-06 | ✓→✗ | ▼ Worse | -81% | 0% |
| case-08 | ✓→✗ | ▼ Worse | -73% | 0% |
| case-14 | ✓→✗ | ▼ Worse | -73% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -76% | 0% |
<objective> Bridge local completion → merged PR. After /gsd-verify-work passes, ship the work: push branch, create PR with auto-generated body, optionally trigger review, and track the merge.
Closes the plan → execute → verify → ship loop. </objective>
<execution_context> @$HOME/.claude/get-shit-done/workflows/ship.md </execution_context>
Execute the ship workflow from @$HOME/.claude/get-shit-done/workflows/ship.md end-to-end.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-19 | fail→fail | 2,849 | 4,199 | +47% | 1 | 1 | 0% | 341 | 349 | +2% | 0 | 0 | — |
case-20 | fail→fail | 14,256 | 4,848 | -66% | 1 | 1 | 0% | 1,134 | 267 | -76% | 0 | 0 | — |
case-13 | fail→fail | 8,933 | 15,019 | +68% | 1 | 1 | 0% | 636 | 344 | -46% | 0 | 0 | — |
case-01 | fail→fail | 6,314 | 10,325 | +64% | 1 | 1 | 0% | 1,022 | 392 | -62% | 0 | 0 | — |
case-02 | fail→fail | 8,741 | 9,421 | +8% | 1 | 1 | 0% | 604 | 301 | -50% | 0 | 0 | — |
case-03 | fail→fail | 11,409 | 10,366 | -9% | 1 | 1 | 0% | 389 | 290 | -25% | 0 | 0 | — |
case-04 | fail→fail | 8,966 | 5,065 | -44% | 1 | 1 | 0% | 256 | 321 | +25% | 0 | 0 | — |
case-05 | fail→fail | 6,360 | 13,050 | +105% | 1 | 1 | 0% | 379 | 329 | -13% | 0 | 0 | — |
case-06 | pass→fail | 12,887 | 4,699 | -64% | 1 | 1 | 0% | 1,337 | 251 | -81% | 0 | 0 | — |
case-07 | fail→fail | 16,246 | 8,980 | -45% | 1 | 1 | 0% | 1,006 | 306 | -70% | 0 | 0 | — |
case-08 | pass→fail | 7,707 | 14,575 | +89% | 1 | 1 | 0% | 1,213 | 325 | -73% | 0 | 0 | — |
case-09 | fail→fail | 11,092 | 9,208 | -17% | 1 | 1 | 0% | 217 | 263 | +21% | 0 | 0 | — |
case-10 | fail→fail | 16,797 | 8,807 | -48% | 1 | 1 | 0% | 284 | 338 | +19% | 0 | 0 | — |
case-11 | fail→fail | 13,277 | 14,392 | +8% | 1 | 1 | 0% | 1,122 | 304 | -73% | 0 | 0 | — |
case-12 | fail→fail | 7,477 | 10,181 | +36% | 1 | 1 | 0% | 310 | 375 | +21% | 0 | 0 | — |
case-14 | pass→fail | 11,824 | 13,594 | +15% | 1 | 1 | 0% | 1,042 | 285 | -73% | 0 | 0 | — |
case-15 | fail→pass | 16,288 | 16,430 | +1% | 1 | 1 | 0% | 245 | 1,933 | +689% | 0 | 0 | — |
case-16 | pass→fail | 9,056 | 16,352 | +81% | 1 | 1 | 0% | 1,110 | 262 | -76% | 0 | 0 | — |
case-17 | fail→fail | 10,177 | 9,190 | -10% | 1 | 1 | 0% | 1,398 | 269 | -81% | 0 | 0 | — |
case-18 | fail→fail | 8,400 | 9,166 | +9% | 1 | 1 | 0% | 1,442 | 290 | -80% | 0 | 0 | — |
case-21 | pass→fail | 5,148 | 5,719 | +11% | 1 | 1 | 0% | 754 | 425 | -44% | 0 | 0 | — |
case-22 | fail→fail | 9,482 | 10,583 | +12% | 1 | 1 | 0% | 1,640 | 241 | -85% | 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 0 counted toward the lift figure. The other 22 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. A headline lift is not published for this run.
Other measured skills in the registry, with their headline benchmark lift.