mcpField
A
article-writing

article-writing

github.com/c0x12cCreative & media109106 installsUpdated 19w ago
Repository

About article-writing

A writing skill for long-form articles, guides, essays, and tutorials, intended for writers who want clear, evidence-based prose. Its process emphasizes concrete openings, concise sections, and editing out unsupported claims and formulaic language.

Key features

  1. 01Long-form article drafting
  2. 02Voice matching from examples
  3. 03Notes and research turned into articles
  4. 04Editing and tightening existing text
  5. 05Evidence-focused writing guidance

Use cases

  1. 01Drafting a blog post or tutorial
  2. 02Turning research notes into an article
  3. 03Revising text to remove filler

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/c0x12c/ai-toolkit --skill article-writing

After installing, type/article-writingin Claude Code to confirm it loaded.

Bundled filesexamples.md

Details

From the project README

Article Writing

Write long-form content that sounds like a person wrote it.

When to Use

  • Blog posts, essays, guides, tutorials
  • Turning notes or research into an article
  • Matching an existing voice from examples
  • Cleaning up and tightening existing writing

See examples.md for good vs bad writing examples that show what "sounds human" actually means.

Rules

  1. Start with something concrete: example, number, story, or code block.
  2. Explain after the example, not before.
  3. Short, direct sentences.
  4. Use real numbers when you have them.
  5. Never make up facts, company data, or quotes.

Banned Patterns

Delete and rewrite any of these:

  • "In today's rapidly evolving landscape"
  • "Moreover", "Furthermore", "Additionally"
  • "game-changer", "cutting-edge", "revolutionary"
  • Vague claims with no proof
  • Bio claims you can't back up

Writing Process

  1. Know the audience and goal
  2. Outline: one purpose per section
  3. Start each section with evidence or example
  4. Only keep sentences that earn their spot
  5. Cut anything that sounds like a template

Structure Tips

Technical Guides
  • Open with what the reader gets
  • Code or terminal examples in every section
  • End with real takeaways, not soft summary
Essays / Opinion
  • Start with tension or a sharp point
  • One argument per section
  • Back opinions with examples
Newsletters
  • First screen must be strong
  • Mix insight with updates
  • Clear section labels, easy to skim

Interaction Style

No BS. Honest feedback only.

This is a two-way talk:

  • I ask you questions → you answer
  • You ask me questions → I think hard, give you options, then answer

When I ask you a question, I always:

  1. Think about it first
  2. Give you 2-3 options with my honest take on each
  3. Tell you which one I'd pick and why
  4. Then ask what you think

When you ask me something:

  • I give you a straight answer
  • I tell you if a section is boring, weak, or filler
  • I push for real examples over vague claims

Never:

  • Ask a question without giving options
  • Let filler paragraphs stay in the draft
  • Say "it depends" without picking a side
  • Skip the "this part is weak" feedback
  • Write AI-sounding content and call it done

Gotchas

  • The intro is where most articles die. If the first paragraph starts with "In this article, we'll explore..." — delete it and start with a story, stat, or code block.
  • AI-written articles all sound the same. They hedge ("it's important to note"), use transition words nobody says out loud ("Moreover"), and avoid strong opinions. Cut all of that.
  • Don't explain the obvious. If your audience is developers, don't explain what an API is. Write for the person, not the lowest common denominator.
  • Long ≠ thorough. A 3,000-word article with 1,500 words of filler is worse than a 1,500-word article where every sentence earns its spot.
  • Every section needs evidence. A claim without a number, example, or code block is just an opinion. Back it up or cut it.

Before You Deliver

  • Facts match sources
  • No filler or corporate talk
  • Voice matches examples (if given)
  • Every section adds something new
  • Format fits the platform

Output

Save to the project's research or build folder depending on context.

Comments

Markdown supported