domains / documents / remove-ai-writing-patterns / avoid-ai-writing

avoid-ai-writing

Skill card

combined

The two copies overlap in purpose (audit and rewrite prose to remove AI-isms) but each contains material steps and constraints the other lacks. The first copy defines a 21-category detection taxonomy, a four-section output format (issues, rewrite, what changed, second-pass audit), and explicit limitations (audit-only mode, preserve technical terms, no code detection). The second copy provides a concrete, tiered replacement table (Tier 1/2/3), specific formatting rules with numeric thresholds (em dash hard max, bold limits, emoji exceptions), and a three-step workflow (audit, rewrite, diff summary). Neither copy is a strict reproduction of the other, so crowning one would hide a real alternative.

Repositories

Other copies

Combined skill

# Avoid AI Writing — Audit & Rewrite

Detect and fix AI writing patterns ("AI-isms") that make text sound machine-generated. Preserve meaning, evidence, factual claims, uncertainty, attributed quotations, code, identifiers, and the writer's voice.

## When to Use

- When asked to "remove AI-isms," "clean up AI writing," or "make this sound less like AI"
- After drafting content with AI and before publishing
- When auditing documentation, blog posts, marketing copy, or internal communications for AI tells

## Workflow

1. **Audit**: Identify every AI-ism present, citing the specific text. Use the detection categories and tiered word list below.
2. **Rewrite**: Return a clean version with all AI-isms removed. Apply the formatting and word-replacement rules.
3. **Diff summary**: Briefly list what you changed and why.
4. **Second-pass audit**: Re-read the rewrite to catch any surviving tells. (If the user requested audit-only, skip steps 2–4 and report findings without rewriting.)

## Detection Categories

Cover these 21 pattern categories:

1. Formatting issues (em dashes, bold overuse, emoji headers, bullet-heavy sections)
2. Sentence structure problems (hedging, hollow intensifiers, rule of three)
3. Word/phrase replacements (see tiered table below)
4. Template phrases
5. Transition phrases
6. Structural issues
7. Significance inflation
8. Copula avoidance
9. Synonym cycling
10. Vague attributions
11. Filler phrases
12. Generic conclusions
13. Chatbot artifacts
14. Notability name-dropping
15. Superficial -ing analyses
16. Promotional language
17. Formulaic challenges
18. False ranges
19. Inline-header lists
20. Title case headings
21. Cutoff disclaimers

## Formatting Rules

- **Em dashes (— and --)**: Replace with commas, periods, parentheses, or rewrite as two sentences. Target: zero. Hard max: one per 1,000 words. Applies to headings and section titles too. Catch both Unicode em dash (—) and double-hyphen substitute (--).
- **Bold overuse**: Strip bold from most phrases. One bolded phrase per major section at most, or none. If something's important enough to bold, restructure the sentence to lead with it instead.
- **Emoji in headers**: Remove entirely. Exception: social posts may use one or two emoji sparingly — at the end of a line, never mid-sentence.
- **Excessive bullet lists**: Convert bullet-heavy sections into prose paragraphs. Bullets only for genuinely list-like content (feature comparisons, step-by-step instructions, API parameters).

## Sentence Structure Rules

- **"It's not X — it's Y" / "This isn't about X, it's about Y"**: Rewrite as a direct positive statement. Max one per piece, and only if it serves the argument.
- **Hollow intensifiers**: Cut `genuine`, `real` (as in "a real improvement"), `truly`, `quite frankly`, `to be honest`, `let's be clear`, `it's worth noting that`. Just state the fact.
- **Hedging**: Cut `perhaps`, `could potentially`, `it's important to note that`, `to be clear`. Make the point directly.
- **Missing bridge sentences**: Each paragraph should connect to the last. If paragraphs could be rearranged without the reader noticing, add connective tissue.
- **Compulsive rule of three**: Vary groupings. Use two items, four items, or a full sentence instead of triads. Max one "adjective, adjective, and adjective" pattern per piece.

## Word/Phrase Replacement Tiers

Words are organized into three tiers based on how reliably they signal AI-generated text. This tiered approach reduces false positives on words that are fine in isolation but suspicious in clusters.

- **Tier 1 — Always flag.** These words appear 5–20x more often in AI text than human text. Replace on sight.
- **Tier 2 — Flag in clusters.** Individually fine, but two or more in the same paragraph is a strong AI signal. Flag when they appear together.
- **Tier 3 — Flag by density.** Common words that AI simply overuses. Only flag when they make up a noticeable fraction of the text (roughly 3%+ of total words).

### Tier 1 — Always replace

| Replace | With |
|---|---|
| delve / delve into | explore, dig into, look at |
| landscape (metaphor) | field, space, industry, world |
| tapestry | (describe the actual complexity) |
| realm | area, field, domain |
| paradigm | model, approach, framework |
| embark | start, begin |
| beacon | (rewrite entirely) |
| testament to | shows, proves, demonstrates |
| robust | strong, reliable, solid |
| comprehensive | thorough, complete, full |
| cutting-edge | latest, newest, advanced |
| leverage (verb) | use |
| pivotal | important, key, critical |
| underscores | highlights, shows |
| meticulous / meticulously | careful, detailed, precise |
| seamless / seamlessly | smooth, easy, without friction |
| game-changer / game-changing | describe what specifically changed and why it matters |
| utilize | use |
| watershed moment | turning point, shift (or describe what changed) |
| marking a pivotal moment | (state what happened) |
| the future looks bright | (cut — say something specific or nothing) |
| only time will tell | (cut — say something specific or nothing) |
| nestled | is located, sits, is in |
| vibrant | (describe what makes it active, or cut) |
| thriving | growing, active (or cite a number) |
| despite challenges… continues to thrive | (name the challenge and the response, or cut) |
| showcasing | showing, demonstrating (or cut the clause) |
| deep dive / dive into | look at, examine, explore |
| unpack / unpacking | explain, break down, walk through |
| bustling | busy, active (or cite what makes it busy) |
| intricate / intricacies | complex, detailed (or name the specific complexity) |
| complexities | (name the actual complexities, or use "problems" / "details") |
| ever-evolving | changing, growing (or describe how) |
| enduring | lasting, long-running (or cite how long) |
| daunting | hard, difficult, challenging |
| holistic / holistically | complete, full, whole (or describe what's included) |
| actionable | practical, useful, concrete |
| impactful | effective, significant (or describe the impact) |
| learnings | lessons, findings, takeaways |
| thought leader / thought leadership | expert, authority (or describe their actual contribution) |
| best practices | what works, proven methods, standard approach |
| at its core | (cut — just state the thing) |
| synergy / synergies | (describe the actual combined effect) |
| interplay | relationship, connection, interaction |

## Limitations

- These are editorial heuristics, not proof of AI authorship.
- For audit-only requests, report findings without rewriting.
- Avoid replacing a precise technical term merely because it appears on a word list.
- Does not detect AI-generated code, only prose.
- Pattern matching is guideline-based, not absolute — some flagged words are fine in context.
- The replacement table suggests alternatives but the best choice depends on context.
- Cannot verify factual claims or find real citations to replace vague attributions.