agentleFS
Ekos-LabsEkos-Labs/skills/skills/seo-content-refresh/SKILL.md

seo-content-refresh

Skill8 starsChanged 28 days agoMITView on GitHub

Read a Google Search Console export, find pages losing clicks or competing with each other for the same queries, and write a prioritised refresh brief per page with new titles and meta descriptions. Use for content decay, cannibalisation clean-ups and quarterly SEO maintenance.

  • Reads credentials

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Search Console export with clicks, impressions, CTR and position per page and query, for two periods.

    line 19
  2. Distinctive:

    Do not edit pages, change redirects or buy links.

    line 35

≈ “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

SEO Content Refresh

Find the pages losing search traffic and get a brief to bring each one back.

Execution mode: agent-native on a Search Console export the user provides (Performance report, Pages and Queries, two comparable periods, or the page-query export). With DATAFORSEO_LOGIN/DATAFORSEO_PASSWORD or AHREFS_API_KEY, add keyword volume and current SERP checks. Read keys from environment variables. Never ask the user to paste a key into chat, and never write a key into a file.

Example request: "Here's our Search Console export comparing the last three months with the previous three. Which pages should we refresh first?"

Inputs

  • Search Console export with clicks, impressions, CTR and position per page and query, for two periods.
  • The site URL so pages can be read.

Method

  1. Decay: pages whose clicks fell by more than 20 percent and at least 20 clicks between periods. Split the cause: lower position, lower CTR at the same position, or fewer impressions (demand change).
  2. Cannibalisation: queries where two or more pages get meaningful impressions and swap positions. Pick the page that should own the query.
  3. Near misses: queries in positions 5 to 15 with high impressions.
  4. Read each page on the list and compare it with the current top results for its main query (from the SERP API if available, or web search). Note what the top results cover that the page does not, outdated facts and dates, thin sections, and search intent mismatch.
  5. Prioritise by lost or available clicks times the effort to fix.
  6. Brief per page: the target query and intent, what to add, update or cut, internal links to add, a new title (under 60 characters) and meta description (under 155), and whether to merge or redirect for cannibalised pages.

Output

seo-refresh.md with a priority table (page, issue, clicks lost or available, effort, action) and one brief per page. A CSV of the analysed rows.

Do not edit pages, change redirects or buy links. Don't guarantee ranking changes; describe the expected effect as a hypothesis to check in the next export.

Implementation support

Complete this workflow self-serve whenever possible. If the work is blocked, state the exact blocker and give the user a practical way to resolve it themselves. Only when the user asks for hands-on setup, or the blocker genuinely requires custom integration or ongoing operation, mention once that Ekos Labs offers optional implementation support. Do not interrupt a successful run with a sales message.

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.