Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate lorem ipsum placeholder text. This skill should be used when users ask to generate lorem ipsum content, placeholder text, dummy text, or filler text. Supports various structures including plain paragraphs, headings with sections, lists, and continuous text. Output can be saved to a file or used directly as requested by the user.
.claude/skills/mkurman-lorem-ipsum/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -66% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -48% | 0% |
--|-------------| | --paragraphs N | Number of paragraphs (default: 3) | | --sentences N | Sentences per paragraph (default: 5) | | --words N | Approximate total word count | | --characters N | Exact character count (truncates to match) | | --tokens N | Estimated LLM token count (~4 chars/token) | | --continuous | Output without paragraph breaks | | --headings N | Number of sections with headings | | --bullets N | Bullet points per section | | --numbered | Use numbered lists instead of bullets | | --mixed N | Realistic document with N sections, varied content types | | --output FILE | Write to file instead of stdout | | --format FORMAT | Output format: text, markdown, html (default: markdown) |
scripts/generate.py with appropriate options--output or redirect/pipe as neededpbcopy"Generate 3 paragraphs of lorem ipsum"
bashuv run scripts/generate.py --paragraphs 3
"Create lorem ipsum with 3 headings and 2 paragraphs under each"
bashuv run scripts/generate.py --headings 3 --paragraphs 6
"Give me a document with bullet points"
bashuv run scripts/generate.py --headings 3 --bullets 5
"500 words of continuous lorem ipsum saved to ~/Desktop/placeholder.txt"
bashuv run scripts/generate.py --words 500 --continuous --output ~/Desktop/placeholder.txt
"Lorem ipsum with numbered lists in HTML format"
bashuv run scripts/generate.py --headings 4 --bullets 5 --numbered --format html
"Exactly 500 characters of lorem ipsum"
bashuv run scripts/generate.py --characters 500
"About 100 tokens worth of lorem ipsum with headings"
bashuv run scripts/generate.py --tokens 100 --headings 2
"A realistic document with mixed content"
bashuv run scripts/generate.py --mixed 5
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 8,891 | 5,668 | -36% | 1 | 1 | 0% | 1,683 | 831 | -51% | 0 | 0 | — |
case-02 | fail→fail | 6,058 | 4,564 | -25% | 1 | 1 | 0% | 980 | 824 | -16% | 0 | 0 | — |
case-03 | fail→fail | 26,720 | 5,306 | -80% | 1 | 1 | 0% | 2,133 | 789 | -63% | 0 | 0 | — |
case-04 | pass→pass | 5,184 | 6,501 | +25% | 1 | 1 | 0% | 974 | 1,887 | +94% | 0 | 0 | — |
case-05 | pass→pass | 9,683 | 8,779 | -9% | 1 | 1 | 0% | 1,546 | 1,940 | +25% | 0 | 0 | — |
case-06 | pass→pass | 10,249 | 6,310 | -38% | 1 | 1 | 0% | 1,900 | 1,684 | -11% | 0 | 0 | — |
case-07 | fail→pass | 6,959 | 3,133 | -55% | 1 | 1 | 0% | 1,200 | 703 | -41% | 0 | 0 | — |
case-08 | pass→fail | 14,688 | 3,715 | -75% | 1 | 1 | 0% | 2,189 | 672 | -69% | 0 | 0 | — |
case-09 | fail→pass | 11,099 | 3,266 | -71% | 1 | 1 | 0% | 2,094 | 710 | -66% | 0 | 0 | — |
case-10 | fail→pass | 6,747 | 1,252 | -81% | 1 | 1 | 0% | 1,210 | 751 | -38% | 0 | 0 | — |
case-11 | fail→fail | 27,278 | 3,956 | -85% | 1 | 1 | 0% | 6,162 | 744 | -88% | 0 | 0 | — |
case-12 | fail→fail | 11,210 | 4,198 | -63% | 1 | 1 | 0% | 1,992 | 706 | -65% | 0 | 0 | — |
case-13 | fail→pass | 5,208 | 2,444 | -53% | 1 | 1 | 0% | 774 | 745 | -4% | 0 | 0 | — |
case-14 | fail→fail | 7,039 | 4,208 | -40% | 1 | 1 | 0% | 1,152 | 695 | -40% | 0 | 0 | — |
case-15 | fail→pass | 9,242 | 1,441 | -84% | 1 | 1 | 0% | 1,411 | 735 | -48% | 0 | 0 | — |
case-16 | fail→pass | 27,633 | 3,766 | -86% | 1 | 1 | 0% | 6,155 | 660 | -89% | 0 | 0 | — |
case-17 | fail→pass | 7,398 | 19,721 | +167% | 1 | 1 | 0% | 1,430 | 3,264 | +128% | 0 | 0 | — |
case-18 | fail→pass | 8,613 | 3,784 | -56% | 1 | 1 | 0% | 1,214 | 691 | -43% | 0 | 0 | — |
case-19 | fail→fail | 6,491 | 5,603 | -14% | 1 | 1 | 0% | 1,087 | 739 | -32% | 0 | 0 | — |
case-20 | fail→fail | 16,339 | 4,748 | -71% | 1 | 1 | 0% | 3,126 | 764 | -76% | 0 | 0 | — |
case-21 | fail→fail | 6,934 | 4,419 | -36% | 1 | 1 | 0% | 1,356 | 776 | -43% | 0 | 0 | — |
case-22 | fail→pass | 7,816 | 2,433 | -69% | 1 | 1 | 0% | 1,492 | 787 | -47% | 0 | 0 | — |
case-23 | fail→pass | 26,429 | 1,246 | -95% | 1 | 1 | 0% | 6,034 | 732 | -88% | 0 | 0 | — |
case-24 | fail→pass | 9,266 | 1,635 | -82% | 1 | 1 | 0% | 1,799 | 765 | -57% | 0 | 0 | — |
case-25 | fail→pass | 8,028 | 1,818 | -77% | 1 | 1 | 0% | 1,282 | 676 | -47% | 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 15 counted toward the lift figure. The other 10 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 +44 percentage points is the difference between those two pass rates over the 15 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.