agentleFS
RightBloggerRightBlogger/bloggingskills/skills/seo-optimize/SKILL.md

seo-optimize

Skill4 starsChanged 14 days agoMITView on GitHub

Tunes an existing draft or published post around one target keyword so its title, opening, and headings match what searchers want, without stuffing. Use when the user says 'optimize this for SEO', 'rank for [keyword]', 'make this more findable', 'make this rank better', or 'help me with SEO' about content that exists. For a new post, see article. For a post losing traffic, see refresh. For meta fields, see meta. For AI citations, see ai-seo.

3 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

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    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:

    If .agents/blog-context.md exists, read it.

    line 20
  2. Distinctive:

    Read house-style/references/ai-tells.md before you touch the draft.

    line 23
  3. Distinctive:

    If the post is old and losing traffic, refresh is the better fit: it diagnoses the decline before editing.

    line 28
  4. Distinctive:

    Place the primary keyword, as a concept inflected naturally, in the title, in at least one H2, and early in the intro.

    line 43
  5. Distinctive:

    Keep SEO, keywords, search intent, and strategy out of the post itself.

    line 63
  6. Distinctive:

    Don't change the URL of a published post unless the user asks.

    line 68

“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

SEO optimize

You take a draft or published post that already exists and tune it around one target keyword, so it reads naturally and answers what searchers came for. You are not writing from scratch, and you never stuff keywords. Readability wins every time.

You're done when the title and opening match what the searcher typed, the headings cover the intent, the related questions are answered, no sentence exists only to hold a keyword, and the author's facts, argument, and voice are intact.

Initial assessment

  • If .agents/blog-context.md exists, read it. The captured author voice and any product or audience notes override the defaults below. Preserve the author's meaning and voice; you are sharpening their piece, not replacing it.
  • Read house-style/references/ai-tells.md before you touch the draft. Every edit you make has to survive that rulebook.
  • Get two inputs: the content (pasted text or a URL) and the primary keyword. If the keyword is missing, infer it from the title and opening, say which one you used, and proceed. If SERP context was provided, keep it handy for step 1.
  • If the post is old and losing traffic, refresh is the better fit: it diagnoses the decline before editing.

Method

  1. Pin the target. Settle on the primary keyword, then gather the related terms and the top reader questions around it. If keyword-research or serp-analysis output is available, pull from it; otherwise infer the obvious related terms and the questions a searcher would type.
  2. Build a short optimization brief: the intent the page must satisfy, the related terms worth working in, the top questions the piece should answer, and any section the ranking pages treat as table stakes that this one lacks. Keep it to a few lines. Leave word count out of it; length follows the question, and Google has no preferred word count.
  3. Edit the draft against the brief:
    • Place the primary keyword, as a concept inflected naturally, in the title, in at least one H2, and early in the intro. Keep the title close to the words a searcher would type; search engines rewrite titles that drift from the page and the query, and AI search cites closely matching titles more often. Never force the exact string where a natural phrasing reads better.
    • Answer the main question in the first few sentences, and open each section with its point. That opening is what skimmers and answer engines take.
    • Weave in only the related terms that are genuinely missing, and only where they read as something a person would write.
    • Make every heading descriptive so the set covers the search intent. Replace generic headings that earn nothing.
    • Tighten structure per house-style: paragraph length, sentence variance, and skimmability. Cut padding rather than add it.
  4. Re-read for stuffing. If any sentence exists to hold a keyword, rewrite or delete it. If the piece now repeats an idea, collapse it. Run the rulebook's self-check on every sentence you wrote or changed.

Hard rules

  • A keyword that hurts the sentence loses. Never repeat the target to hit a count.
  • Keep SEO, keywords, search intent, and strategy out of the post itself. The reader sees an article, not the machinery behind it. The notes below the post are for the author, so plain talk about keywords is fine there.
  • Optimize this one page. Never propose near-duplicate pages for keyword variations; that's scaled content abuse and it splits the page's strength.
  • Don't change the URL of a published post unless the user asks; if they do, they need a redirect.

Output

Return the optimized draft first. Then, below a --- separator, give the brief in a few lines and a short change list in plain terms: what you added, moved, or rewrote, and why it helps the reader find or follow the piece. No jargon, no keyword-density talk. If the post is published, note whether the change is substantial enough to update its "last updated" date.

Related skills

article · refresh · humanize · meta · internal-links · ai-seo · keyword-research · serp-analysis · house-style

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.