agentleFS
milad-ahmdmilad-ahmd/agent-skills/skills/seo-blog-writer/SKILL.md

seo-blog-writer

Skill5 starsChanged 19 days agoMITView on GitHub

Researches and writes SEO-optimized, genuinely helpful blog articles, covering keyword and search-intent analysis, competitor outline gaps, title and meta description, headings, FAQ, internal links, and schema, in the brand's voice and following Google's helpful-content and E-E-A-T principles. Use when the user asks to write a blog post or article, do SEO content, or rank for a keyword.

8 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 5 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. Distinctive:

    E-E-A-T: ask for first-hand experience, data, examples, author credentials and screenshots that only this brand can provide.

    line 15
  2. Distinctive:

    Use keywords naturally, never stuffed.

    line 31
  3. Distinctive:

    Add an FAQ section built from real questions, 3–5 internal link suggestions and 2–3 authoritative external sources.

    line 32
  4. Very specific:

    No invented statistics, quotes or sources.

    line 42
  5. Distinctive:

    No AI filler phrases ("In today's digital landscape", "delve", "it's important to note").

    line 43
  6. Distinctive:

    Write in the brand's voice.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 5 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 Blog Writer

Content that ranks because it is the most helpful answer to the search.

1. Research

  • Primary keyword + intent: informational, commercial, transactional or navigational. Match the format that is already ranking (guide, listicle, comparison, tutorial).
  • Analyse the top results (with a search or browser tool if available, otherwise from the user's input): their headings, depth, angle, and gaps they miss.
  • Collect secondary keywords, related questions (People Also Ask) and entities.
  • E-E-A-T: ask for first-hand experience, data, examples, author credentials and screenshots that only this brand can provide.

2. Brief and outline (get approval before writing)

Title (≤ 60 chars, keyword early) ×3 options
Meta description (≤ 155 chars, benefit + keyword) ×2
URL slug: /short-keyword-slug
H1 → H2/H3 outline with intent of each section and target word count
Unique angle / information gain: what we add that others don't

3. Write

  • Answer the query in the first 100 words, then go deeper.
  • Short paragraphs, descriptive headings, lists, tables and examples. Write at an 8th–10th grade reading level.
  • Use keywords naturally, never stuffed. Cover the topic completely.
  • Add an FAQ section built from real questions, 3–5 internal link suggestions and 2–3 authoritative external sources.
  • Suggest images with alt text, and FAQ or Article JSON-LD schema.
  • End with a clear CTA that matches the search intent.

4. Optimise

A checklist covering: the keyword in the title, H1, intro, one H2, the slug and the meta description; images compressed with alt text; internal links; scannability; and a freshness date.

Rules

  • No invented statistics, quotes or sources. Mark anything uncertain [VERIFY] and cite real sources.
  • No AI filler phrases ("In today's digital landscape", "delve", "it's important to note").
  • Write in the brand's voice. Ask for samples.
  • Output Markdown, ready for the user's CMS (WordPress, Ghost, Webflow, MDX).

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.