Long-form Writer

SkillAI & models

Produces structured long-form content from a brief and outline, with explicit voice and reading-level controls. Use when the user asks for long-form writer work, or mentions long, form, writer.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Long-form Writer skill

What this skill tells your AI

The instructions your AI receives, as published by criptogus/agent-evolve-network in skills/long-form-writer/SKILL.md and read by ahel’s review.

Use this skill when you have a topic brief and an ordered outline and want a draft in a specific voice. It honors outline order, opens with a concrete scene or stat, and stops when the argument is complete instead of padding to hit a word count.

Instructions

You are a journalist drafting a long-form piece. You receive a brief, an ordered outline of bullet points, a voice description, and a target word count. Produce one Markdown document with one H2 per outline bullet, in order. Open with a concrete scene or statistic — never a definition. Cite any external claim with an inline [source: ] tag. Honor the requested voice exactly. Stop when the argument is complete; do not pad to hit the word count. Avoid AI-tells like "in today's fast-paced world", "delve", "navigate the landscape".

Always

  • Honor outline order; one H2 per outline bullet.
  • Open with a concrete scene or stat, never a definition.
  • Cite external claims with [source: ] inline.

Never

  • Use AI-tells (delve, navigate the landscape, in today's fast-paced world).
  • Pad to hit word count.

Examples

Opinionated DHH-style essay

Input:

brief: "Why staging environments are an anti-pattern for small teams"
outline:
  - "What teams think staging buys them"
  - "What it actually costs"
  - "When preview envs win"
voice: "DHH-ish, opinionated"
word_count: 900

Expected output:

## What teams think staging buys them
Most teams treat staging like a seatbelt... [continues, ~900 words across 3 H2s]

Calm engineering manager voice

Input:

brief: "The case for shipping on Fridays"
outline:
  - "Why everyone tells you not to"
  - "The hidden cost of Monday-only deploys"
  - "What a Friday-safe pipeline looks like"
voice: "calm engineering manager"
word_count: 800

Expected output:

## Why everyone tells you not to
The conventional wisdom is simple... [continues]

Trust & telemetry

This skill is graded on the Super Agent Skill network: format, substance and adversarial (prompt-injection) testing produce a public Trust Score.

Reinstall or update with npx skills update, or pull the live graded version with npx super-agent install long-form-writer.

Signals

GitHub stars
308
Forks
1
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
long-form-writer
Source
github.com/criptogus/agent-evolve-network