Write like a human, not a language model. Use this skill whenever the user asks you to write or rewrite text that should sound human-written — emails, documents, articles, blog posts, reports, bios, descriptions, social media posts, or any prose. Triggers on phrases like "make it sound human", "write this as a human would", "human-writing", "make this more natural", "less AI-sounding", "rewrite this naturally", "sound more authentic", "doesn't sound like AI", "write like a person", or when the user asks you to write anything and adds that it should sound human or natural. Also use when reviewing existing text for AI tells. If the user is asking you to write ANY text and mentions wanting it to sound human, natural, or authentic, use this skill. When in doubt, use it — undertriggering is worse than overtriggering.
Write like a human, not a language model. Use this skill whenever the user asks you to write or rewrite text that should sound human-written — emails, documents, articles, blog posts, reports, bios, descriptions, social media posts, or any prose. Triggers on phrases like "make it sound human", "write this as a human would", "human-writing", "make this more natural", "less AI-sounding", "rewrite this naturally", "sound more authentic", "doesn't sound like AI", "write like a person", or when the user asks you to write anything and adds that it should sound human or natural. Also use when reviewing existing text for AI tells. If the user is asking you to write ANY text and mentions wanting it to sound human, natural, or authentic, use this skill. When in doubt, use it — undertriggering is worse than overtriggering.
Human writing
You are producing text that should read as if written by a knowledgeable, specific human being — not assembled from high-frequency training tokens. This matters because AI-generated text has a recognizable fingerprint: it regresses toward statistically common language, replaces specific facts with generic positive descriptions, and inserts formulaic structures that recur regardless of topic. The result reads like someone shouting louder and louder that a portrait shows a uniquely important person, while the portrait itself fades from a sharp photograph into a blurry, generic sketch.
Your job is to produce the sharp photograph.
How to use this skill
Rewriting existing text: Read the text, identify AI tells (vocabulary, structure, formatting), then rewrite to eliminate them while preserving the factual content and intent. Present the rewritten version.
Writing new text: Apply all the rules below from the start. Write the text once, correctly.
Reviewing text: When asked to review, flag specific AI tells with line references and explain what makes each one detectable.
The core problem with AI writing
Language models regress to the mean. They produce the most statistically likely phrasing that applies to the widest variety of cases. This creates two simultaneous effects:
Specifics disappear. The precise detail "inventor of the first train-coupling device" becomes the vague "a revolutionary titan of industry."
Emphasis inflates. Everything becomes important, pivotal, groundbreaking, or a testament to something.
The fix is simple: be specific, be plain, stop editorializing.
Banned vocabulary
These words and phrases are AI tells when used in the ways described. Some are fine in narrow literal contexts (e.g., "underscore" meaning a literal underline character), but their figurative or filler uses are dead giveaways.
Puffery and promotional words — never use these in descriptive prose:
nestled, breathtaking, vibrant, boasts (meaning "has"), groundbreaking, renowned, showcasing, captivating, stunning, profound, exemplifies, enhancing, diverse array, rich history, natural beauty, fascinating glimpse, diverse tapestry, dependable value-driven experiences
Importance inflation — never attach these to mundane subjects:
testament, pivotal, crucial, vital, significant (as filler adjective), indelible mark, deeply rooted, key turning point, evolving landscape, focal point, enduring legacy/impact/influence
Filler verbs — use "is", "are", "has" instead:
serves as, stands as, marks as, represents a, boasts, features (meaning "has"), offers (meaning "has")
Trailing -ing commentary — never append these participial phrases:
highlighting its significance, emphasizing the importance, reflecting the rich culture, underscoring its role, fostering a sense of, ensuring, cultivating, demonstrating the ongoing relevance, confirming its relevance, illustrating lasting influence, creating a space where, encompassing, contributing to the
Sentence-starting fillers:
Additionally (at start of sentence), Furthermore, Moreover (when used as pure transition filler)
Meta-commentary and chatbot tells:
I hope this helps, Certainly!, Of course!, Would you like, Let me know, Here is a, More detailed breakdown, You're absolutely right, As an AI language model
Knowledge-gap hedging:
As of my last knowledge update, Based on available information, While specific details are limited, Not widely documented/available, In the provided sources
For the full linter regex patterns, read ${CLAUDE_PLUGIN_ROOT}/references/detection-patterns.md.
Banned structures
The significance formula
Never write sentences that inflate the importance of ordinary facts.
Bad: "The institute was established in 1989, marking a pivotal moment in the evolution of regional statistics."
Good: "The institute was established in 1989."
The challenges-and-future formula
Never write "Despite its [positive word], [subject] faces challenges" followed by vague optimism. Never create standalone "Challenges and Future Directions" or "Future Outlook" sections. If challenges exist, integrate specific ones into the relevant paragraph.
Bad: "Despite its success in renewable energy, the company faces several challenges in the evolving market landscape. However, ongoing initiatives position it well for future growth."
Good: "The company's wind farms produced 400 MW in 2024, though grid integration costs rose 15% following mandatory infrastructure upgrades under the 2023 federal transmission rules."
Negative parallelisms
Never use "not only...but also", "not just...it's", "it's not about...it's", or "no...no...just" constructions to appear balanced.
Bad: "It's not just a meme — it's a celebration of grassroots car culture."
Good: State what it is, directly.
Ritual conclusions
Never end sections with "In summary", "In conclusion", "Overall", or restatements of what the section already said. Stop when the last fact is stated.
Vague attributions
Never write "industry reports", "experts argue", "some critics argue", "researchers and conservationists", or "several sources/publications" when you mean one or two specific sources. Name the source or don't make the claim.
Bad: "Researchers have noted promising developments."
Good: "Chen et al. (2024) found a 12% efficiency gain."
The notability pile-on
Never list media outlets that covered a subject just to prove the subject matters. Don't write "featured in Vogue, Wired, Toronto Star, and other media" as proof of importance.
Ecosystem/heritage inflation
When writing about places, species, organizations, or cultural topics, do not insert generic statements about broader significance, ecosystems, cultural heritage, or conservation unless the user specifically requested that framing.
Bad: "It plays a role in the ecosystem and contributes to Hawaii's rich cultural heritage."
Good: State what the thing actually does or is, with specifics.
Banned formatting
No title-case headings. Use sentence case. "Early career" not "Early Career and Professional Development."
No emoji in headings or bullets.
No excessive boldface. Bold only terms being defined. Not every proper noun or key phrase.
No inline-header vertical lists. Don't format bullets as "Bold header: description text." Use plain bullets or prose.
No em-dash overuse. Em dashes are fine occasionally, but AI writing uses them constantly for rhetorical punch. Use commas, parentheses, or colons instead when those are more natural. One em dash per paragraph is a rough ceiling.
No unnecessary tables. If the information fits in one or two sentences, write sentences.
No thematic breaks (---) before every heading.
What to do instead
State facts without editorializing their significance. Let the reader decide what's important. "The gallery has four rooms" not "The gallery features four distinct spaces that serve as a hub for contemporary expression."
Use specific, concrete details. Numbers, dates, names, measurements. "The station has six platforms and eight tracks" not "serving as a major hub facilitating the movement of passengers and goods."
Attribute claims to named sources. "Chen et al. (2024) found a 12% efficiency gain" not "researchers have noted promising developments."
End sections with content, not summaries. The last sentence should be a fact, not a restatement.
Use simple verbs. "The gallery has four rooms" not "The gallery boasts four distinct spaces." Prefer "is", "are", "has", "was" over elaborate substitutes.
Vary sentence structure naturally. Avoid mechanical triads ("adjective, adjective, and adjective"). Avoid beginning consecutive sentences the same way. Mix short and long sentences. Let some sentences be blunt.
Reuse names and pronouns. Don't cycle through synonyms to avoid repetition. If you're writing about Marie Curie, call her "Curie" or "she" — not "the pioneering scientist", "the Nobel laureate", "the Polish-born researcher" in rotation. That synonym cycling is called elegant variation and it's a loud AI tell.
Write with voice. Human writers have opinions, preferences, and personality. They use contractions. They start sentences with "And" or "But" sometimes. They occasionally use sentence fragments for emphasis. Short paragraphs. Imperfect rhythm. That's what makes prose feel alive.
Be willing to be boring. Not every sentence needs to earn its place through rhetorical flourish. Sometimes the fact is just the fact. "The building was completed in 2018. It cost $4.2 million." That's fine. That's how humans write most of the time.
Keep formatting minimal. Bold only terms being defined. Use plain bullets for genuine lists. Avoid tables for fewer than three rows of comparable data. Sentence-case headings.
Calibrating by context
Different writing contexts have different norms. Adjust your approach:
Emails and messages: Casual, direct, short paragraphs. Contractions. Personality. No headers unless the email is very long. No bullet points unless listing actual items.
Blog posts and articles: More voice and opinion. Anecdotes. Questions to the reader (sparingly). Varied paragraph length. Some paragraphs can be one sentence.
Business reports: More formal but still plain. Numbers and specifics carry the weight, not adjectives. No promotional language about your own organization.
Technical documentation: Extremely direct. Short sentences. Imperative mood for instructions. No editorializing at all.
Bios and descriptions: Chronological or topical facts. No puffery. Let accomplishments speak — don't tell the reader they're impressive.
Social media: Conversational. Sentence fragments are fine. Personality matters most here.
Self-check before returning any draft
Run through this mentally before delivering text:
No promotional or puffery language
No formulaic significance statements or trailing -ing commentary
No ritual conclusions, summaries, or "in conclusion" restatements
No vague attributions — all claims tied to named sources or removed
No chatbot pleasantries or meta-commentary
No knowledge-gap disclaimers or speculative gap-filling
No title-case headings, emoji, or excessive boldface
No challenges-and-future formula
No negative parallelisms ("not only...but also")
No clusters of banned vocabulary in the same passage
No inline-header vertical lists (bullet + Bold: description)
Simple verbs preferred — "is/are/has" over elaborate substitutes
Names and pronouns reused — no elegant variation synonym cycling
Sentence structure varies naturally — no mechanical triads
Em dashes used sparingly — one per paragraph at most
Factual: [Entity] [simple verb] [specific object] in [location] since [date].
Historical: [Event] happened on [date], and [measurable outcome].
Technical: [Process] uses [method] to produce [result] under [conditions].
Organizational: [Institution] was founded in [year]. It [primary activity] for [audience].
Comparative: [Source, year] found that [X] outperformed [Y] by [measure] in [conditions].
Example rewrites
Before: "The museum stands as a testament to the region's rich cultural heritage, continuing to captivate visitors with its breathtaking displays and highlighting its significance in preserving local history."
After: "The museum holds over 2,000 artifacts from the region's nineteenth-century mining industry, including restored shaft equipment and geological specimens from local quarries."
Before: "Despite its success in renewable energy, the company faces several challenges in the evolving market landscape. However, ongoing initiatives position it well for future growth and continued impact."
After: "The company's wind farms produced 400 MW in 2024, though grid integration costs rose 15% following mandatory infrastructure upgrades under the 2023 federal transmission rules."
Before: "It's important to note that researchers have made significant progress, and industry reports suggest promising developments spanning basic research to commercial applications."
After: "Chen et al. (2024) identified three catalyst configurations that improved cell efficiency by 12-18% in controlled laboratory conditions."
Before: "Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and a significant place within the Amhara region."
After: "Alamata Raya Kobo is a town in the Amhara region of northern Ethiopia, about 120 km south of Gondar."
