agentleFS
UXMagicaiUXMagicai/seosorted-skills/skills/write-article/SKILL.md

write-article

Skill0 starsChanged 39 days agoMITView on GitHub

Write and generate one SEO article with SEOsorted's pipeline — SERP research, competitor analysis, grounded research with citations, outline, draft, humanizing, internal links, images in the workspace's preset style, and meta tags. Use when the user asks to write a blog post, article, guide or how-to for a keyword, or to create content for their site.

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never paste a "generated" article you wrote yourself into the workspace as if SEOsorted produced it.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 3 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

Write one article

SEOsorted writes in the workspace's own brand voice, image preset and research settings. The agent's job is choosing the right target, giving a sharp brief, and checking the result.

Steps

  1. Target. Confirm the primary keyword. If it came from a list, it has volume and KD; if the user typed it, get metrics with research_keywords operation: "metrics".
  2. Overlap. check_keyword_overlap with the keyword and compare_existing: true. If an existing page already owns the intent, recommend content-refresh instead.
  3. Draft. manage_articles operation: "create_draft" with primary_keyword, optional title, content_type (BLOG_POST, PILLAR_GUIDE, HOWTO, LISTICLE — comparison pages use write_comparison_page), secondary_keywords, and a brief when there is a specific angle, audience or must-cover point. If the response carries an overlap warning, read it before continuing.
  4. Generate. Tell the user it uses one article credit (charged when it finishes), then write_articles operation: "start" with the article_ids. Poll check_job_status (wait_seconds: 45) — generation usually takes 4–7 minutes.
  5. Review. manage_articles operation: "get". Check: the H1 matches the intent, facts carry sources, nothing promises outcomes on YMYL topics, internal links point at real pages, no meta-commentary about "the sources provided". Report issues honestly with the exact passage.
  6. Score. improve_article operation: "health" and "recommendations" with article_id (free) — fix failing checks before publishing; update-and-republish covers the edits and image changes.

Output

Title, word count, URL slug, meta title/description, image count, and anything that needs a human edit. Then offer content-calendar to schedule it or publish-to-cms to publish now.

Guardrails

Never paste a "generated" article you wrote yourself into the workspace as if SEOsorted produced it. If the user wants their own copy, create the draft with their text as the brief and say so.

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.