Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments,
.claude/skills/mkurman-docx/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -52% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 2% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | -44% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 78% | 0% |
npm install -g docx (new documents)scripts/office/soffice.py)pdftoppm for images| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 4,502 | 7,411 | +65% | 1 | 1 | 0% | 705 | 474 | -33% | 0 | 0 | — |
case-02 | fail→fail | 5,288 | 4,425 | -16% | 1 | 1 | 0% | 1,037 | 257 | -75% | 0 | 0 | — |
case-03 | fail→fail | 29,232 | 57,479 | +97% | 1 | 1 | 0% | 6,165 | 12,265 | +99% | 0 | 0 | — |
case-04 | pass→pass | 7,563 | 3,374 | -55% | 1 | 1 | 0% | 1,399 | 670 | -52% | 0 | 0 | — |
case-21 | pass→pass | 8,352 | 8,332 | -0% | 1 | 1 | 0% | 1,472 | 1,496 | +2% | 0 | 0 | — |
case-05 | pass→pass | 6,219 | 3,013 | -52% | 1 | 1 | 0% | 999 | 564 | -44% | 0 | 0 | — |
case-06 | pass→pass | 16,149 | 28,758 | +78% | 1 | 1 | 0% | 3,518 | 6,246 | +78% | 0 | 0 | — |
case-07 | pass→pass | 8,210 | 4,257 | -48% | 1 | 1 | 0% | 1,473 | 796 | -46% | 0 | 0 | — |
case-08 | pass→pass | 8,106 | 4,077 | -50% | 1 | 1 | 0% | 1,528 | 776 | -49% | 0 | 0 | — |
case-09 | pass→pass | 8,690 | 5,771 | -34% | 1 | 1 | 0% | 1,521 | 1,265 | -17% | 0 | 0 | — |
case-10 | pass→pass | 10,318 | 5,949 | -42% | 1 | 1 | 0% | 1,885 | 1,172 | -38% | 0 | 0 | — |
case-11 | pass→pass | 8,025 | 3,415 | -57% | 1 | 1 | 0% | 1,278 | 601 | -53% | 0 | 0 | — |
case-12 | pass→pass | 5,209 | 3,154 | -39% | 1 | 1 | 0% | 1,019 | 640 | -37% | 0 | 0 | — |
case-13 | pass→pass | 6,681 | 3,889 | -42% | 1 | 1 | 0% | 1,083 | 679 | -37% | 0 | 0 | — |
case-14 | pass→pass | 7,819 | 7,996 | +2% | 1 | 1 | 0% | 1,585 | 1,682 | +6% | 0 | 0 | — |
case-15 | pass→pass | 7,640 | 3,040 | -60% | 1 | 1 | 0% | 1,477 | 627 | -58% | 0 | 0 | — |
case-16 | pass→pass | 10,586 | 7,791 | -26% | 1 | 1 | 0% | 1,770 | 1,729 | -2% | 0 | 0 | — |
case-17 | pass→pass | 8,170 | 2,170 | -73% | 1 | 1 | 0% | 1,423 | 439 | -69% | 0 | 0 | — |
case-18 | pass→pass | 9,457 | 6,252 | -34% | 1 | 1 | 0% | 1,688 | 1,263 | -25% | 0 | 0 | — |
case-19 | pass→pass | 11,430 | 6,514 | -43% | 1 | 1 | 0% | 1,781 | 1,197 | -33% | 0 | 0 | — |
case-20 | pass→pass | 9,732 | 8,038 | -17% | 1 | 1 | 0% | 1,659 | 1,546 | -7% | 0 | 0 | — |
case-22 | pass→pass | 7,887 | 3,580 | -55% | 1 | 1 | 0% | 1,411 | 792 | -44% | 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 21 counted toward the lift figure. The other 1 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 +5 percentage points is the difference between those two pass rates over the 21 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.