human-writing-style

name	human-writing-style
description	Write technical articles and long-form content that reads authentically — like a specific person explaining their experience, not AI-generated filler. Use when creating articles, tutorials, or any written content where authenticity matters.

Human Writing Style

This skill guides creation of technical content that reads authentically. The output should feel like something written by a person explaining their experience, not content generated to fill space.

Writing Philosophy

AI writing is detectable through four tells:

• Vocabulary tells: Overuse of "delve," "crucial," "landscape," "harness," "foster"
• Structural tells: Uniform paragraph lengths, excessive parallelism, formulaic transitions
• Tone tells: Hedging everything, lacking opinions, inflating mundane details
• Format tells: Overuse of em dashes, all-bullets OR all-prose (never mixing)

The goal is not to "hide" AI authorship but to produce genuinely good writing that avoids these patterns.

Vocabulary Blacklist

NEVER use:

• delve, dive into, explore (as metaphors)
• crucial, pivotal, significant, notable, remarkably
• landscape, realm, paradigm, tapestry
• harness, leverage, utilize, facilitate
• foster, enable, empower
• "It's worth noting that..."
• "In today's world..." / "In the age of..."
• "When it comes to..."
• "At the end of the day..."
• "This is where X comes in..."
• "Let's unpack..."
• "Certainly!", "Absolutely!", "Great question!"

Also avoid:

• Parallel negation overuse ("It's not X, it's Y" more than once per article)
• Em dashes for emphasis (limit to 1–2 per article)
• Starting multiple consecutive sentences with "This"

Sentence Construction

Do:

• Vary sentence length aggressively (3 words to 30 words)
• Use fragments for emphasis ("No bot detector needed." / "Brutal.")
• Start sentences with "But," "And," "So" naturally
• Use contractions (don't, isn't, can't, won't)

Don't:

• Make every sentence the same length
• Start consecutive sentences the same way
• Hedge every claim with "may," "might," "could potentially"

Structure Rules

Use bullet points for:

• Lists of items, features, options, or steps
• Before/after comparisons
• Key takeaways
• Technical specifications

Use prose for:

• Opening hooks and context-setting
• Narrative transitions
• Emotional beats
• Closing thoughts

Mix both within sections: 1–2 sentences of prose → bullets for details → prose for transition.

Tone Guidelines

Be direct:

• "This was killing me" not "This presented a significant challenge"
• State opinions without excessive hedging

Be specific:

• Include actual numbers (40%, 60–70%, 20+ templates)
• Include real before/after examples
• Name real tools, frameworks, features

Be honest about uncertainty:

• "I don't have rigorous A/B test data"
• Don't overclaim results

Show personality:

• Include reactions ("This surprised me," "Here's what clicked")
• Acknowledge tradeoffs and downsides
• Use humor sparingly but genuinely

Formatting Guidelines

Headers:

• Conversational, not formal ("What my bot was doing wrong" not "Problem Analysis")
• Questions work well as headers
• 3–8 words

Code blocks:

• Include real snippets
• 3–8 lines ideal
• One sentence of context before explaining

Bold:

• Bold key terms at start of bullet items
• Bold numbered list headers
• Don't bold for emphasis in prose — word choice does that

Pre-Delivery Checklist

• No vocabulary from the blacklist
• Mix of prose and bullets
• At least one specific number or percentage
• At least one concrete before/after example
• Sentence lengths visibly vary
• Headers are conversational
• Contractions used naturally
• No more than 1–2 em dashes total
• Opening hook is about the problem/situation, not the topic abstractly
• Closing is a specific insight, not a generic summary

Critical test: not "does this avoid AI tells" but "does this read like something a specific person actually wrote?"