Article Writing
Draft blogs, guides, launch posts, and newsletter issues that stay on-brand without sounding like generic AI copy.
Overview
Article Writing is an agent skill most often used in Grow (also Launch, Validate) that drafts and refines long-form content in a distinctive, evidence-led voice without inventing facts.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill article-writingWhat is this skill?
- Activates for blog posts, essays, guides, tutorials, and newsletter issues from notes or transcripts
- Five core rules: lead with concrete proof, explain after the example, tight sentences, no invented facts
- Integrates with brand-voice via reused VOICE PROFILE instead of duplicating style analysis
- Banned-pattern pass to strip typical LLM smoothing and paste voice
- Default sharp operator voice when no brand examples are supplied
- 5 core writing rules
- 4 When to Activate trigger scenarios
Adoption & trust: 5.4k installs on skills.sh; 210k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have ideas, notes, or a rough draft but the output reads like generic LLM paste and does not sound like you or your brand.
Who is it for?
Founders and indie builders shipping essays, tutorials, launch narratives, or newsletter issues who care about voice, structure, and factual discipline.
Skip if: One-line social posts, pure SEO keyword stuffing without a point of view, or cases where you want the model to fabricate testimonials or metrics.
When should I use this skill?
User wants polished written content longer than a paragraph—articles, guides, blog posts, tutorials, newsletter issues—especially when voice consistency, structure, and credibility matter.
What do I get? / Deliverables
You get structured long-form copy that leads with proof, matches your voice profile when provided, and is ready to publish or iterate—run brand-voice first when a specific voice is required.
- Polished long-form article or guide draft
- Restructured copy with proof-led openings and banned-pattern rewrites
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Long-form publishing and lifecycle content compound in Grow, even though the same skill also supports launch and landing copy earlier in the journey. Content subphase is the canonical shelf for repeatable articles, tutorials, and editorial assets—not one-off social snippets.
Where it fits
Turn validation notes into landing-page narrative that leads with a concrete artifact instead of vague promise copy.
Draft a launch essay or changelog story for distribution channels with tight pacing and proof-first paragraphs.
Produce tutorial or guide series that matches an existing operator voice from brand-voice examples.
Shape onboarding or lifecycle email sequences into credible long-form sections when voice consistency matters.
How it compares
Use for governed long-form voice and structure—not as a substitute for brand-voice when you need a formal style profile first.
Common Questions / FAQ
Who is article-writing for?
Solo and indie builders who publish blogs, guides, launch posts, or newsletters and need credible, non-generic long-form copy aligned to an operator or brand voice.
When should I use article-writing?
Use it in Grow for content and lifecycle editorial, in Launch for distribution posts and guides, and in Validate when turning research into landing or scope narratives—any time you need polished copy longer than a paragraph.
Is article-writing safe to install?
Treat it like any third-party skill: review the Security Audits panel on this Prism page and only enable it in agents you trust with your drafts and brand materials.
Workflow Chain
Requires first: brand voice
SKILL.md
READMESKILL.md - Article Writing
# Article Writing Write long-form content that sounds like an actual person with a point of view, not an LLM smoothing itself into paste. ## When to Activate - drafting blog posts, essays, launch posts, guides, tutorials, or newsletter issues - turning notes, transcripts, or research into polished articles - matching an existing founder, operator, or brand voice from examples - tightening structure, pacing, and evidence in already-written long-form copy ## Core Rules 1. Lead with the concrete thing: artifact, example, output, anecdote, number, screenshot, or code. 2. Explain after the example, not before. 3. Keep sentences tight unless the source voice is intentionally expansive. 4. Use proof instead of adjectives. 5. Never invent facts, credibility, or customer evidence. ## Voice Handling If the user wants a specific voice, run `brand-voice` first and reuse its `VOICE PROFILE`. Do not duplicate a second style-analysis pass here unless the user explicitly asks for one. If no voice references are given, default to a sharp operator voice: concrete, unsentimental, useful. ## Banned Patterns Delete and rewrite any of these: - "In today's rapidly evolving landscape" - "game-changer", "cutting-edge", "revolutionary" - "here's why this matters" as a standalone bridge - fake vulnerability arcs - a closing question added only to juice engagement - biography padding that does not move the argument - generic AI throat-clearing that delays the point ## Writing Process 1. Clarify the audience and purpose. 2. Build a hard outline with one job per section. 3. Start sections with proof, artifact, conflict, or example. 4. Expand only where the next sentence earns space. 5. Cut anything that sounds templated, overexplained, or self-congratulatory. ## Structure Guidance ### Technical Guides - open with what the reader gets - use code, commands, screenshots, or concrete output in major sections - end with actionable takeaways, not a soft recap ### Essays / Opinion - start with tension, contradiction, or a specific observation - keep one argument thread per section - make opinions answer to evidence ### Newsletters - keep the first screen doing real work - do not front-load diary filler - use section labels only when they improve scanability ## Quality Gate Before delivering: - factual claims are backed by provided sources - generic AI transitions are gone - the voice matches the supplied examples or the agreed `VOICE PROFILE` - every section adds something new - formatting matches the intended medium