agentleFS
Sign inStart free
UXMagicaiUXMagicai/seosorted-skills/skills/content-refresh/SKILL.md

content-refresh

Skill0 starsChanged 39 days agoMITView on GitHub

Find and improve existing pages that are close to ranking (page 2, positions 8–20), losing clicks, or getting impressions without clicks, using SEOsorted's Search Console and GA4 data, then edit and republish them. Use when the user asks to optimize existing content, refresh old posts, fix declining traffic, improve CTR, find quick SEO wins, or update articles that dropped.

7 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

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    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:

    If there is no Search Console data, stop and explain how to connect it.

    line 17
  2. Distinctive:

    Write a concrete plan per page: new title/meta (within 60 / 160 characters), sections to add with the query each targets, facts to update …

    line 34

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

Pages that already rank on page 2 have authority. Moving them up is usually faster than ranking a new page.

1. Pick the pages

  1. get_search_traffic with days: 90 and each of:
    • view: "opportunities" — query/page pairs ranking 8–20, ranked by clicks a top position would add.
    • view: "decaying" — articles whose average position fell 3+ places.
    • view: "top_pages" — page-one queries whose CTR is well below the benchmark (title and description worth rewriting).
    • view: "content_performance" (needs GA4) — articles whose sessions fell 30%+. If there is no Search Console data, stop and explain how to connect it. All views are free.
  2. Pick 3–10 pages with the most impressions at risk or within reach.

2. Diagnose each page

  1. get_search_traffic view: "page" with page_url — its queries and position changes.
  2. Find the SEOsorted article: manage_articles operation: "list" with search, then operation: "get" with article_id.
  3. improve_article operation: "health" (score, failing checks, 30-day clicks and queries) and operation: "recommendations" (prioritised fixes). Free.
  4. check_google_results operation: "results" with the top query (1 keyword lookup credit) — what now ranks above it and which SERP features (AI Overview, People Also Ask) it competes with.
  5. Diagnose with evidence:
    • Ranks for queries the page barely covers → add a section answering them.
    • High impressions, low CTR at a good position → new title and meta description around the top query.
    • Decaying → outdated facts, prices or dates; competitors added depth.
    • Two pages splitting the same queries → cannibalization-check, then merge.

3. Edit plan, then apply

Write a concrete plan per page: new title/meta (within 60 / 160 characters), sections to add with the query each targets, facts to update with sources. Show it and get a yes.

Apply with update-and-republish: improve_article (suggest_meta with apply: true, rewrite, suggest_links), manage_articles operation: "update" for title, body or meta, then publish_articles operation: "republish" with confirm: true — only after the user approves pushing it live. None of the edits use article credits.

Non-SEOsorted pages are edited in the user's CMS; hand over the plan.

Re-check with get_search_traffic view: "page" after 2–4 weeks.

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