agentleFS
Sign inStart free
ZachArticulateVZachArticulateV/designer-pro-and-seo/skills/content-draft/SKILL.md

content-draft

Skill10 starsChanged 25 days agoMITView on GitHub

Draft long-form content (blog post, service page, landing page, guide) from a brief or outline — structured, on-intent, and originality-checked, ready for human edit. Trigger when the user says "draft this", "write the blog post", "write the page", "turn this brief into content", "first draft", or has an outline/brief and needs the actual content written.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Originality + accuracy pass: Remove generic-AI phrasing.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

content-draft

Family: content-and-data Status: Stable

Purpose

Turn a brief or outline into an actual first draft — the production counterpart to the analysis skills. Fills the hole between seo-content-brief (which plans) and seo-content (which audits): neither writes the content. This does, on-intent and structured for both human readers and AI-search citability.

Triggers

  • "draft this" / "first draft"
  • "write the blog post" / "write the page" / "write this guide"
  • "turn this brief into content"

Inputs

  • A brief or outline (from seo-content-brief, or pasted) — or just a topic + target keyword + intent
  • Audience and search intent
  • Tone / brand voice (or pull from a design system)
  • Target length / section structure

Steps

  1. Confirm intent and structure. Restate the search intent and the section outline (use the brief's per-section word counts if available).
  2. Draft section by section. Open with a direct answer to the query (good for readers and AI Overviews), then develop each section. Make each paragraph one clear, source-able claim.
  3. Weave keywords naturally — primary in title/H1/intro, related terms across sections; never stuff.
  4. Add structure for citability — descriptive H2/H3s, lists/tables where they aid scanning, a short TL;DR, and FAQ where intent is question-led.
  5. Originality + accuracy pass. Remove generic-AI phrasing; mark any factual claim that needs a source with [cite] so the human editor can verify.
  6. Hand off to seo-content (E-E-A-T audit) and seo-page (on-page checks) before publishing. Always label output as a first draft for human edit.

Outputs

  • A structured first draft matching the brief
  • [cite] markers on claims that need verification
  • A short list of what a human editor should confirm (facts, brand specifics)

Dependencies

  • None required (pure method). Composes with seo-content-brief (upstream), seo-content + seo-page (downstream review).

Notes

This produces a first draft, not final copy — it explicitly flags claims to verify and is meant to be edited by a human with subject-matter knowledge. That caveat protects against publishing unverified AI text (an E-E-A-T and trust risk).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free