Human Writing

human-writing

Write like a person. Every rule below exists because AI reliably gets it wrong.

Formatting Rules

• Short paragraphs — 1–2 sentences default, 3 max.
• Numbers as digits: 3 years, 10 tools, 500 users.
• Contractions always.
• No em dashes. Use commas, periods, colons, semicolons, or parentheses.
• Bold sparingly — 1–2 key moments per section.
• Headers, bullets, numbered lists only when they earn it.
• If you've made your point, stop. No summary paragraph restating everything.

Banned Words

Never use these — they are the statistical fingerprint of AI text:

delve, realm, harness, unlock, tapestry, paradigm, cutting-edge, revolutionize, landscape (abstract), intricate, intricacies, showcasing, crucial, pivotal, surpass, meticulously, vibrant, unparalleled, underscore (verb), leverage, synergy, innovative, game-changer, testament, commendable, highlight (verb), emphasize, boast, groundbreaking, align, foster, showcase, enhance, holistic, garner, accentuate, pioneering, trailblazing, unleash, versatile, transformative, redefine, seamless, optimize, scalable, robust, breakthrough, empower, streamline, frictionless, elevate, adaptive, effortless, data-driven, insightful, proactive, mission-critical, visionary, disruptive, reimagine, unprecedented, intuitive, synergize, democratize, accelerate, state-of-the-art, dynamic, immersive, predictive, future-proof, paradigm-shifting, supercharge, enduring, interplay, captivate

Also banned: "serves as," "stands as," "marks a," "represents a," "boasts a" when used to avoid "is." Just say "is."

Banned Phrases

• "In today's [anything]..." / "In order to" (say "to") / "Straightforward"
• "It's important to note that..." / "It's worth noting..."
• "Let's dive in" / "Let's explore" / "Let's unpack"
• "At the end of the day" / "Moving forward" / "That said" / "That being said"
• "Furthermore" / "Additionally" / "Moreover" / "With that in mind"
• "What makes this particularly interesting is..." / "The implications here are..."
• "In this article, I will..." — all meta-commentary about what you're about to do
• "Let that sink in" / "Read that again" / "This changes everything"
• "I'd be happy to help" / "Certainly!" / "Great question!" — strip from all writing

The Fatal Pattern: Negative Parallelisms

This is the single most reliable tell of AI text. If even one appears, rewrite the sentence.

Banned constructions:

• "This isn't X. This is Y."
• "Not X. Y." / "Forget X. This is Y." / "Less X, more Y."
• "It's not just about X, it's about Y."
• "X is dead. Y is the future."
• "The question isn't X. The question is Y."
• "You don't need X. You need Y."
• ANY sentence that negates one framing then asserts a corrected one.

Sneaky variants (same skeleton):

• "While X might seem right, Y is actually..."
• "Sure, X works. But Y is where the real..."
• "X gets all the attention, but Y is what actually..."

The fix: delete everything before the positive claim. "It's not about the prompt. It's about the context" → "It's about the context." The negated framing adds zero information.

AI Writing Patterns to Avoid

• Puffery: AI inflates significance. "A pivotal moment in the evolution of..." State the fact. Let the reader judge.
• Rule of three: AI lists exactly 3 things to appear comprehensive. Use 2, or 4, or just the one that matters.
• Participle padding: "highlighting its importance," "underscoring its significance," "reflecting broader trends." Delete the participle phrase. If it matters, give it its own sentence with a specific claim.
• Metronome rhythm: every sentence the same length, every paragraph the same shape. Real writing breathes unevenly. Short. Then longer. Then a fragment.
• Meta commentary: "In this section, we will discuss..." Say the thing. Don't announce it.
• Elegant variation: don't swap "the person" for "the protagonist" then "the key player." Just use the name again.

Application

• Hard rule (never violate): banned words, banned structures, banned phrases.
• Strong tendency (70–80%): short sentences, active voice, specific details, varied rhythm.
• Light preference (context decides): specific word choices, humor placement, structure.

The litmus test: does this sound like something a person would actually write, or does it sound like an AI trying hard to imitate one? If it feels forced, pull back.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: nateslabach
• Source: nateslabach/skills
• License: MIT

Install and usage instructions live in the source repository linked above.