seo-content
Skill30 starsChanged 5 months agoMITView on GitHub
Write a publish-ready, search-optimized article for a target keyword: SERP-validated brief, full draft matched to search intent, on-page metadata (title tag, meta description, URL slug), and schema markup. Use when the user says 'write a blog post about X', 'write an article that ranks', 'create SEO content', 'I need content for this keyword', or hands over a keyword/content brief from an SEO plan — even if they never say 'SEO'. Also use to rewrite or upgrade an existing article that isn't ranking. Produces the complete article plus a metadata block and an on-page checklist result.
43 other projects use a version of this.
Adopted by
Most recently taken up by
- stimulir/managed-skillstheir own version, first seen Nov 16, 2026
- martinbattaglia-commits/Claude-skillstheir own version, first seen Nov 16, 2026
- yotamwiesel/claude-skillstheir own version, first seen Nov 16, 2026
- mia-cx/skillstheir own version, first seen Nov 15, 2026
- joaoguirunas/team-ostheir own version, first seen Nov 15, 2026
- YerayRodri/claude-skillstheir own version, first seen Nov 13, 2026
Used with
Projects with it also use seo-agentic, seo-image-gen and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AgriciDanielSkillseo-agentic
Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Use when the user asks whether AI agents can use or browse the site, or about llms.txt or WebMCP. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).
Also in 5 projects that use this
timruebenachSkillseo-image-gen
AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says \"generate image\", \"OG image\", \"social preview\", \"hero image\", \"blog image\", \"product photo\", \"infographic\", \"seo image\", \"create visual\", \"image-gen\", \"favicon\", \"schema image\", \"pinterest pin\", \"generate visual\", \"banner\", or \"thumbnail\".
Also in 17 projects that use this
megastepSkillseo-competitor-pages
Generate SEO-optimized competitor comparison and alternatives pages. Covers "X vs Y" layouts, "alternatives to X" pages, feature matrices, schema markup, and conversion optimization. Use when user says "comparison page", "vs page", "alternatives page", "competitor comparison", or "X vs Y".
Also in 25 projects that use this
megastepSkillseo-sitemap
Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure. Use when user says "sitemap", "generate sitemap", "sitemap issues", or "XML sitemap".
Also in 26 projects that use this
timruebenachSkillseo-cluster
SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations. Optionally executes content creation if claude-blog is installed. Use when user says "topic cluster", "content cluster", "semantic clustering", "pillar page", "hub and spoke", "content architecture", "keyword grouping", or "cluster plan".
Also in 16 projects that use this
mangollcSkillseo-backlinks
Backlink analysis and link building strategy: competitor backlink profiling, outreach plan generation, monthly SEO reporting framework, toxic link identification, link opportunity scoring, and unlinked mention discovery.
Also in 18 projects that use this
- +2 more from megastep
- +3 more from timruebenach
Other versions43 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 43
- AgriciDaniel/claude-seo★ 30ksame name
- genspark-ai/genoffice★ 12ksame name
- zhtyyx/codex-seo★ 152same name
- mangollc/claude-seo-skill★ 39same name
- MoizIbnYousaf/marketing-cli★ 33same name
- coopersimson96/ai-content-system★ 17same name
- ZachArticulateV/designer-pro-and-seo★ 10same name
- bestdeejay-design/agent-skills★ 6same name
- joaoguirunas/team-os★ 6same name
- oegeyilmaz9/seo-aeo-geo-ultimate★ 6same name
33 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository39 other files it gives its agents.
- brand-assetSkill
- creative-strategistSkill
- image-generationSkill
- orchestratorSkill
- original-designSkill
- product-photographySkill
- product-videoSkill
- remotion-script-writerSkill
- social-graphicsSkill
- talking-headSkill
- accessibility-excellenceSkill
- color-systemSkill
- component-architectureSkill
- design-engineer-mindsetSkill
- design-foundationSkill
- error-handling-recoverySkill
- frontend-orchestratorSkill
- interaction-physicsSkill
- layout-systemSkill
- loading-statesSkill
- performance-optimizationSkill
- typography-systemSkill
- visual-hierarchy-refactoringSkill
- brand-voiceSkill
- content-atomizerSkill
- direct-response-copySkill
- email-sequencesSkill
- keyword-researchSkill
- lead-magnetSkill
- newsletterSkill
- orchestratorSkill
- positioning-anglesSkill
- seo-strategySkill
- tweet-writerSkill
- product-design-reviewSkill
- fable-like-implementationSkill
- foundation-sprintSkill
- sol-orchestratorSkill
- sprint-runnerSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 39 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use for writing or rewriting a single search-targeted article (blog post, guide, listicle, comparison).
- Very specific: line 13
If the user has no keyword and no strategy — asks "what should I even write about?" — run skills/marketing/seo-strategy (or …
- Very specific: line 14
If the piece is a landing/sales page where conversion beats ranking, use skills/marketing/direct-response-copy.
- Very specific: line 15
If the user wants social or email derivatives of an article, that's skills/marketing/content-atomizer.
- Distinctive: line 19
Ask in one batch, only what's missing:
- Very specific: line 26
If the request arrives from skills/marketing/seo-strategy with a keyword, intent, and SERP notes, skip straight to Step 2.
- Distinctive: line 32
Search the target keyword (use web search when available).
- Very specific: line 58
Read references/article-templates.md for the full skeleton of the chosen format (How-To, Listicle, or Ultimate Guide) and follow it.
- Distinctive: line 75
Run the quality bar below.
- Distinctive: line 114
Check every item; fix before delivering:
“Common” is measured: kept by at least 6 in 10 of the 39 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.
Files
SEO Content
Write one article that ranks and reads: search-optimized for the target keyword, genuinely useful to the human who typed it. Prime directive: match search intent exactly — Google rewards the format searchers want, and the wrong format doesn't rank no matter how good the writing is. The second directive: every article must contain something the current top results don't (an example, data point, angle, or depth), or there is no reason for it to outrank them.
When to use / when not to
- Use for writing or rewriting a single search-targeted article (blog post, guide, listicle, comparison).
- If the user has no keyword and no strategy — asks "what should I even write about?" — run
skills/marketing/seo-strategy(orskills/marketing/keyword-researchfor just a keyword list) first. - If the piece is a landing/sales page where conversion beats ranking, use
skills/marketing/direct-response-copy. - If the user wants social or email derivatives of an article, that's
skills/marketing/content-atomizer.
Intake
Ask in one batch, only what's missing:
- Target keyword (and secondary keywords if they have them).
- Audience and product — who reads this, and what does the business want the reader to do next (the CTA)?
- Unique material — first-hand experience, examples, data, or customer stories you can use. This is the E-E-A-T fuel; press for at least one concrete item.
- Voice — an existing brand-voice guide or 2–3 sample posts to match. If
skills/marketing/brand-voiceoutput exists, use it.
If the request arrives from skills/marketing/seo-strategy with a keyword, intent, and SERP notes, skip straight to Step 2. If details are missing, state assumptions (audience, intent, CTA) and proceed — don't stall.
Workflow
1. Validate the SERP and lock the intent
Search the target keyword (use web search when available). Classify intent and let it dictate format:
| Intent | Searcher wants | You write |
| Informational | to learn/do | How-to guide or ultimate guide |
| Commercial | to compare/choose | Listicle, comparison, review |
| Transactional | to buy | Product/pricing page → hand off to skills/marketing/direct-response-copy |
| Navigational | a specific brand | Usually skip — you can't outrank the brand |
Note from the top 5 results: content length and depth, structure, subtopics covered, and — most importantly — the gap: what's thin, outdated, unanswered, or missing. If you cannot name a gap, tell the user the keyword is a bad bet and suggest returning to skills/marketing/seo-strategy for a better target. If web search is unavailable, say so, infer intent from the keyword's grammar, and label the SERP analysis as assumption.
2. Write the brief
Fill this in before drafting (it becomes part of the deliverable):
- Primary keyword, secondary keywords, intent, target length
- Content angle: the one-line reason this article beats the current results
- H2 outline (5–8 sections for a full article), including an FAQ section
- E-E-A-T elements: which first-hand example/data goes where
- Internal links (3–5 pages on the user's site), external links (2–3 authoritative sources)
- CTA: the single action the reader is asked to take
Length by competition (heuristic — comprehensiveness is the real target, padding actively hurts): low competition 1,500–2,000 words; medium 2,000–3,000; high 3,000+. Never exceed what the intent needs.
3. Draft
Read references/article-templates.md for the full skeleton of the chosen format (How-To, Listicle, or Ultimate Guide) and follow it. While drafting:
- Open by answering the query in the first 2–3 sentences, then earn continued reading. No throat-clearing intros.
- Keyword placement: title tag (early), H1, first 100 words, 2–3 natural body uses, URL slug. Secondary keywords in H2s where natural. Never stuff.
- Structure: one H1; H2 every major section; subhead every 200–300 words; paragraphs ≤3 sentences; bullets for any list of 3+; bold the takeaways.
- E-E-A-T on the page: at least one first-hand example or case; cite 2–3 authoritative external sources; concrete numbers over vague claims.
- FAQ section: 4–6 exact-phrasing questions with 40–60 word answers (featured-snippet bait).
- Close with 3–5 bullet takeaways and exactly one CTA.
The user supplies lived experience; you supply structure and polish. Never fabricate first-hand experience, testimonials, or statistics — if the user gave no unique material, use clearly-general examples and tell them where to insert their own.
4. Metadata and schema
Produce: title tag (50–60 chars, keyword early, compelling), meta description (150–160 chars, keyword + soft CTA), URL slug (short, keyword, hyphenated), image alt-text suggestions, and JSON-LD schema (FAQ schema if there's an FAQ; Article schema otherwise — copy-paste blocks in references/article-templates.md).
5. Self-review, then deliver
Run the quality bar below. Fix failures before presenting. Deliver in the required output format, and recommend tracking via Google Search Console (impressions, clicks, CTR, average position) with a check-in after the article has had time to index and settle.
Required output format
# [Article Title]
## Brief
- Primary keyword: … · Secondary: … · Intent: [type]
- Angle (why this beats the SERP): …
- Target length: … · CTA: …
- Gap exploited: [what top results miss]
## Metadata
- Title tag (50–60 chars): "…" [char count]
- Meta description (150–160 chars): "…" [char count]
- URL slug: /…
- Schema: [FAQ / Article] (JSON-LD below article)
## Article
[Full draft, H1 through conclusion, with [INTERNAL LINK: page] and
[EXTERNAL LINK: source] markers inline, image suggestions as
[IMAGE: description — alt text: "…"]]
## Schema markup
```json
[JSON-LD block]
```
## On-page checklist
[Each quality-bar item with pass/fail]
## Next steps
- Insert your own examples at: [marked spots, if any]
- Track in GSC: [what to watch, and the decision each signal triggers]Quality bar
Check every item; fix before delivering:
- Format matches validated search intent
- Title tag 50–60 chars with keyword; meta description 150–160 chars — count the characters, don't eyeball
- Exactly one H1, containing the primary keyword; keyword in first 100 words
- Primary keyword used 2–3× in body — no more (stuffing check: read headings aloud; if they sound robotic, rewrite)
- Named gap vs. top results is actually filled in the draft
- ≥1 first-hand example or clearly-marked placeholder for one; every statistic cited or removed; no invented experience or testimonials
- 3–5 internal link markers, 2–3 authoritative external link markers
- FAQ answers 40–60 words each
- Exactly one CTA
- Scannable: no paragraph >3 sentences, subhead every 200–300 words
Integration
skills/marketing/seo-strategy— feeds this skill the keyword, intent, cluster, and SERP notes; return the published-article slug so internal linking stays current.skills/marketing/keyword-research— alternative lighter-weight source of the target keyword.skills/marketing/brand-voice— supplies the voice guide applied in Step 3.skills/marketing/direct-response-copy— takes over for transactional-intent pages and CTA-heavy sections.skills/marketing/content-atomizer— consumes the finished article as seed content for social posts, threads, and newsletter items.skills/marketing/newsletter— the article is a natural feature item; pass the title, link, and one-sentence hook.
References
references/article-templates.md— full H1→conclusion skeletons for the How-To Guide, Listicle/Roundup, and Ultimate Guide formats, plus copy-paste FAQ and Article JSON-LD schema. Read it at Step 3, before drafting.
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
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.

