Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit and rewrite content to remove 21 categories of AI writing patterns with a 43-entry replacement table
.claude/skills/sickn33-avoid-ai-writing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 27% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -4% | 0% |
| case-11 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
| case-12 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
Detects and fixes AI writing patterns ("AI-isms") that make text sound machine-generated. Covers 21 pattern categories with a 43-entry word/phrase replacement table that maps each flagged term to a specific, plainer alternative.
21 pattern categories: formatting issues (em dashes, bold overuse, emoji headers, bullet-heavy sections), sentence structure problems (hedging, hollow intensifiers, rule of three), word/phrase replacements (43 entries like leverage→use, utilize→use, robust→reliable), template phrases, transition phrases, structural issues, significance inflation, copula avoidance, synonym cycling, vague attributions, filler phrases, generic conclusions, chatbot artifacts, notability name-dropping, superficial -ing analyses, promotional language, formulaic challenges, false ranges, inline-header lists, title case headings, and cutoff disclaimers.
Prompt:
Audit this for AI writing patterns:
"In today's rapidly evolving AI landscape, developers are embarking on a pivotal journey to leverage cutting-edge tools that streamline their workflows. Moreover, these robust solutions serve as a testament to the industry's commitment to fostering seamless experiences."Output: The skill returns four sections:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→fail | 6,951 | 5,533 | -20% | 1 | 1 | 0% | 1,226 | 1,409 | +15% | 0 | 0 | — |
case-01 | fail→fail | 9,071 | 6,402 | -29% | 1 | 1 | 0% | 1,496 | 1,665 | +11% | 0 | 0 | — |
case-02 | pass→pass | 6,426 | 5,467 | -15% | 1 | 1 | 0% | 1,194 | 1,513 | +27% | 0 | 0 | — |
case-03 | pass→pass | 10,529 | 6,097 | -42% | 1 | 1 | 0% | 1,827 | 1,761 | -4% | 0 | 0 | — |
case-04 | fail→fail | 9,483 | 6,738 | -29% | 1 | 1 | 0% | 1,789 | 1,796 | +0% | 0 | 0 | — |
case-11 | pass→pass | 8,835 | 6,120 | -31% | 1 | 1 | 0% | 1,400 | 1,656 | +18% | 0 | 0 | — |
case-05 | fail→pass | 17,944 | 8,424 | -53% | 1 | 1 | 0% | 3,383 | 1,961 | -42% | 0 | 0 | — |
case-06 | fail→fail | 3,751 | 4,251 | +13% | 1 | 1 | 0% | 604 | 1,276 | +111% | 0 | 0 | — |
case-07 | fail→fail | 8,950 | 4,970 | -44% | 1 | 1 | 0% | 1,494 | 1,479 | -1% | 0 | 0 | — |
case-08 | fail→fail | 8,392 | 7,880 | -6% | 1 | 1 | 0% | 1,501 | 1,479 | -1% | 0 | 0 | — |
case-09 | fail→fail | 6,546 | 5,474 | -16% | 1 | 1 | 0% | 1,233 | 1,481 | +20% | 0 | 0 | — |
case-12 | pass→pass | 8,861 | 6,820 | -23% | 1 | 1 | 0% | 1,688 | 1,689 | +0% | 0 | 0 | — |
case-13 | fail→fail | 6,858 | 5,003 | -27% | 1 | 1 | 0% | 1,226 | 1,533 | +25% | 0 | 0 | — |
case-14 | pass→pass | 10,221 | 6,314 | -38% | 1 | 1 | 0% | 1,806 | 1,674 | -7% | 0 | 0 | — |
case-15 | fail→fail | 7,095 | 6,249 | -12% | 1 | 1 | 0% | 1,449 | 1,703 | +18% | 0 | 0 | — |
case-16 | pass→pass | 4,816 | 5,248 | +9% | 1 | 1 | 0% | 995 | 1,624 | +63% | 0 | 0 | — |
case-17 | pass→pass | 4,880 | 4,489 | -8% | 1 | 1 | 0% | 894 | 1,397 | +56% | 0 | 0 | — |
case-18 | pass→pass | 7,316 | 5,127 | -30% | 1 | 1 | 0% | 1,172 | 1,440 | +23% | 0 | 0 | — |
case-19 | pass→pass | 7,820 | 5,125 | -34% | 1 | 1 | 0% | 1,316 | 1,430 | +9% | 0 | 0 | — |
case-20 | pass→pass | 7,106 | 4,187 | -41% | 1 | 1 | 0% | 1,488 | 1,302 | -13% | 0 | 0 | — |
case-21 | fail→fail | 9,193 | 7,146 | -22% | 1 | 1 | 0% | 1,634 | 1,755 | +7% | 0 | 0 | — |
case-22 | pass→pass | 8,748 | 5,797 | -34% | 1 | 1 | 0% | 1,445 | 1,416 | -2% | 0 | 0 | — |
case-23 | pass→pass | 9,194 | 6,047 | -34% | 1 | 1 | 0% | 1,603 | 1,589 | -1% | 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. 23 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 23 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.