agentleFS
UXMagicaiUXMagicai/seosorted-skills/skills/update-and-republish/SKILL.md

update-and-republish

Skill0 starsChanged 40 days agoMITView on GitHub

Edit an existing SEOsorted article and push the update live — score it, rewrite passages, humanise, fix the title, meta description and slug, add internal links, regenerate the featured image or add section images, then republish to the CMS with the user's confirmation. Use when the user asks to edit, update, improve, fix or rewrite an article, change its images, or push changes to a published post.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    Only after the user says yes, run it with confirm: true.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Update and republish

None of these edits use article credits. Every body edit keeps the previous version as a revision.

1. Find and score

  1. manage_articles operation: "list" with search (title) to get the article_id; operation: "get" for the body, meta and live URL.
  2. improve_article operation: "health" — content score with each check, readability, keyword density and, if published, 30-day Search Console clicks and queries. operation: "recommendations" — prioritised fixes.

2. Edit

Pick what the user asked for (or what the recommendations call for):

  • Meta: improve_article operation: "suggest_meta"; show it, then again with apply: true to write it.
  • A passage: improve_article operation: "rewrite" with selection (quoted exactly from the body) and instruction or preset (concise, data, hook, humanise, formal, casual). It replaces the passage unless apply: false — use apply: false to preview first.
  • Whole body reads machine-written: operation: "humanise".
  • Internal links: operation: "suggest_links" returns anchors already in the body with targets; apply the ones the user accepts via a body update.
  • Missing keywords: operation: "suggest_keywords".
  • First-hand experience: operation: "questions" returns author-interview questions; pass answers to save the user's replies.
  • Direct edits: manage_articles operation: "update" with any of title, meta_title, meta_description, slug, focus_keyword, secondary_keywords, brief, or body. body replaces everything — read with get first and send the whole edited text. Changing the slug of a live post changes its URL; warn the user and recommend a redirect.

3. Images

manage_article_images with article_id (no article credits; 10–40 seconds each):

  • operation: "list" — current images and the style in effect.
  • operation: "regenerate_featured" — new featured image, source: "AI" (optional prompt) or "UNSPLASH" (optional query), with alt.
  • operation: "generate_inline" with heading (exact H2–H4 text) to illustrate that section, or only prompt to get an image URL and markdown without placing it.

4. Push live

A published article keeps showing the old text and images until it is republished.

  1. Re-run improve_article operation: "health" and summarise what changed.
  2. publish_articles operation: "republish" with article_id and dryRun: true; show what will happen.
  3. Only after the user says yes, run it with confirm: true. It is refused when nothing changed since the last publish. Failures → get_publishing_calendar operation: "deliveries" with article_id.

Deleting an article is a separate, permanent step (delete_article, needs confirm: true) — only when the user explicitly asks.

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.