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

Lead with the concrete thing: artifact, example, output, anecdote, number, screenshot, or code.
Explain after the example, not before.
Keep sentences tight unless the source voice is intentionally expansive.
Use proof instead of adjectives.
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

Clarify the audience and purpose.
Build a hard outline with one job per section.
Start sections with proof, artifact, conflict, or example.
Expand only where the next sentence earns space.
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

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Safety

95

Quality

82

Clarity

85

Completeness

73

Summary

This skill guides AI agents to write long-form content (articles, blog posts, guides, newsletters) in a distinctive, consistent voice. It emphasizes concrete evidence-first writing, bans clichéd phrases, and provides structural guidance for different content types. The skill optionally integrates with a `brand-voice` skill for voice consistency and includes a quality gate checklist before delivery.

Detected Capabilities

long-form content generationvoice analysis and matching (via brand-voice integration)structural outlining for different content typescliché detection and rewritingevidence-first writing guidancequality assurance checklist for factual accuracy

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

write blog postdraft article with voicenewsletter contentpolish long-form writingmatch brand voicetechnical tutorialturn notes into article

Use Cases

draft blog posts or launch announcements with founder voice
convert research notes or transcripts into polished articles
write technical tutorials with clear structure and examples
compose newsletter issues with engaging first sections
match existing brand or operator voice across multiple articles
rewrite flabby copy to tighten pacing and remove filler

Quality Notes

Positive: Clear, actionable core rules (lead with concrete, explain after, cut padding) give agents specific directives rather than vague guidance.
Positive: Explicit 'Banned Patterns' section is unusually specific—agents can unambiguously identify and rewrite clichés.
Positive: Integration point with `brand-voice` skill is documented, reducing redundant voice analysis.
Positive: Quality gate at the end provides a checkpoint (factual verification, voice match, no generic transitions).
Positive: Structure guidance is tailored to content type (technical, opinion, newsletter), not one-size-fits-all.
Minor: 'Default to a sharp operator voice' is clear but could benefit from 1–2 sentence example of what that sounds like in practice.
Minor: No guidance on length targets (e.g., 'aim for 1,500–2,500 words') or reading-time expectations, which can matter for newsletters or blog posts.
Minor: Factual claims backing requirement in quality gate is important, but skill does not explain *how* agent should verify sources (spot-check against provided links? ask user?). Assumes user provides sources but does not enforce this upfront.

Model: claude-haiku-4-5-20251001Analyzed: Apr 20, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.2

Content updated

2026-04-20

Latest

v1.1