agentleFS
khadinakbarlabskhadinakbarlabs/vibeseo-plugin/skills/content-refresh/SKILL.md

content-refresh

Skill0 starsChanged 32 days agoMITView on GitHub

Improve an existing SEO page through a keep/change/add plan, evidence checks, intent alignment, content gaps and draft edits. Use for outdated content, a declining page, keyword cannibalization, refresh planning or on-page optimization. Uses the actual page and authorized exports; separates an edit proposal from a verified ranking improvement.

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:

    Read shared rules. Reuse brief guidance for evidence and drafting.

    line 8
  2. Distinctive:

    If requested, draft the changed sections with citations and unresolved facts marked.

    line 14

“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

Read shared rules. Reuse brief guidance for evidence and drafting.

  1. Obtain the actual page text/URL or an authorized export and its date. Reuse business context and goal. Ask for the page if it is necessary and missing; don't pretend a URL alone supplies its content.
  2. Audit its current intent, title/H1, structure, answer quality, originality, facts, links, CTA and product claims. Preserve useful sections, existing URLs and first-hand evidence. Do not recommend a full rewrite by default.
  3. Compare with supplied or approved sampled SERP data and relevant user-owned Search Console exports. Check matching windows/markets before treating a decline as real. Account for seasonality, tracking changes and differing query mixes; don't assert causation.
  4. Produce a Keep / Change / Add / Remove table: exact section, evidence, proposed edit, expected user benefit and validation. Flag competing pages for review and preserve ownership/intent rather than merge or redirect without authorization.
  5. If requested, draft the changed sections with citations and unresolved facts marked. Include title/meta options, verified internal-link suggestions, and visible-content-matching structured data recommendations where appropriate. No keyword stuffing, fabricated experience or bulk templated content.
  6. Define an implementation checklist and a proposed matched follow-up observation window. Changes are proposals until the user applies/authorizes them. Indexing, rank movement and conversions are observations to verify later, not outcomes of producing an edit plan.

Output a focused refresh plan and requested draft edits. Use report template; hand matched ranking measurement to rank-tracking.

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.