seo-content
Skill6 starsChanged 3 months agoApache-2.0View on GitHub
Use when auditing, briefing, rewriting, or reviewing site content for a defined audience, page purpose, locale, and evidence set; produce human-reviewable content improvements without formulaic SEO or AI-citation guarantees.
40 other projects use a version of this.
Adopted by
Most recently taken up by
- mia-cx/skillstheir own version, first seen Nov 15, 2026
- joaoguirunas/team-ostheir own version, first seen Nov 15, 2026
- alpit-patel/seo-aeo-geo-kittheir own version, first seen Nov 8, 2026
- MoizIbnYousaf/marketing-clitheir own version, first seen Nov 1, 2026
- zhtyyx/codex-seotheir own version, first seen Nov 1, 2026
- genspark-ai/genofficetheir own version, first seen Oct 25, 2026
Used with
Projects with it also use seo-image-gen, seo-cluster and 4 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.
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 16 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 15 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 17 projects that use this
- +3 more from timruebenach
Other versions40 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 40
- 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
- sanky369/vibe-building-skills★ 30same 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
30 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 repository27 other files it gives its agents.
- llms.txtllms.txt
- ai-search-researchSkill
- ai-visibility-monitorSkill
- optimise-seoSkill
- seo-action-planSkill
- seo-aeoSkill
- seo-agenticSkill
- seo-architectureSkill
- seo-auditSkill
- seo-authoritySkill
- seo-commerceSkill
- seo-competitor-pagesSkill
- seo-geoSkill
- seo-hreflangSkill
- seo-imagesSkill
- seo-localSkill
- seo-news-discoverSkill
- seo-pageSkill
- seo-performanceSkill
- seo-planSkill
- seo-programmaticSkill
- seo-researchSkill
- seo-schemaSkill
- seo-sitemapSkill
- seoSkill
- seo-technicalSkill
- seo-videoSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 37 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Read markdown-delivery-contract.md for every task.
- Very specific: line 17
Create evidence-led content audits, briefs, and draft improvements that help a real reader complete a task.
- Very specific: line 19
Read references/editorial-brief-protocol.md before preparing a formal brief or draft.
- Distinctive: line 20
Read snippet-copy-protocol.md when title or meta-description copy is part of the deliverable.
- Distinctive: line 24
Ask for or inspect the page/content capture, intended reader and decision/task, locale, page purpose, current factual sources, and any …
- Distinctive: line 40
Use direct answers where the reader asks a direct question, but retain conditions, dates, qualifications, and ownership of the fact.
- Distinctive: line 42
Prefer specific examples, methods, screenshots, original research, expert review, or transparent limits over generic “thought leadership.”
- Distinctive: line 43
Use internal links only to verified, useful destinations.
- Distinctive: line 44
Treat title, H1, meta description, headings, lists, tables, alt text, and schema as reader-facing/technical choices with their own …
- Distinctive: line 64
Do not output a universal content score, minimum word-count mandate, keyword-density target, rigid readability target, or guaranteed …
“Common” is measured: kept by at least 6 in 10 of the 37 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
Markdown delivery contract
Read markdown-delivery-contract.md for every task. Write a substantive .md document for every material work step and register its direct destination in the work index.md. For public-site work, apply the owner-required Markdown discovery profile across the full eligible inventory; preserve native standards and immutable evidence formats.
Lane outputs: content-review.md; content-decisions.md (combine small related steps with stable section links). Create substantive public .md bodies from the same approved source as HTML. Preserve evidence, entity facts, prices/limits, locale, media meaning and freshness. Add natural query language and direct answer sections; do not create AI-only facts or hidden keyword text.
Purpose
Create evidence-led content audits, briefs, and draft improvements that help a real reader complete a task. Use this after an approved seo-action-plan when the request stems from AEO/GEO findings; use it directly for a bounded editorial review with supplied content and facts.
Read references/editorial-brief-protocol.md before preparing a formal brief or draft.
Read snippet-copy-protocol.md when title or meta-description copy is part of the deliverable.
Input gate
Ask for or inspect the page/content capture, intended reader and decision/task, locale, page purpose, current factual sources, and any relevant approved action-plan item. Treat a missing fact, source, audience, or locale as an explicit limitation instead of filling it with plausible copy.
For regulated, health, legal, financial, safety, pricing, availability, or comparative claims, require an owner-approved source and human review. Do not use a search snippet, an AI answer, or a competitor page as proof of a claim.
Workflow
- Frame the job. Identify the reader’s task, search/referral context if known, page type, conversion or information goal, language/region, and what the page must not claim.
- Build a claim ledger. Separate verified facts, interpretation, customer proof, quotations, and unknowns. Pin each factual claim to a supplied source or flag it for verification.
- Diagnose usefulness. Review whether the page answers the actual task, makes ownership and scope clear, offers original evidence or experience where relevant, explains limitations, and is navigable on a small screen. Describe observations; do not assign an E-E-A-T, readability, word-count, or “AI readiness” score.
- Create the brief and query contract. Define the answer/decision the reader needs, primary need/query family, natural supporting language, evidence to show, proposed hierarchy, necessary comparison/steps, entities, internal destinations that are known to exist, media/accessibility needs, locale constraints, CTA, and review owner. Choose headings and metadata for clarity, not fixed character, keyword-density, or passage-length formulas.
- Write complete search-result copy when requested. Produce the actual unique title and meta-description candidate, not “improve metadata” as a placeholder. The description must identify the page, communicate the useful outcome, include a truthful differentiator or concrete page-specific detail, and retain any material qualifier. Rewrite descriptions that are generic, duplicated, fragmentary, or too short to explain why this result fits the query; do not pad them to hit a character count.
- Draft only within approved scope. Supply rewrite options or an implementation-ready draft only from the claim ledger. Keep placeholders unmistakable. Preserve meaningful nuance; do not pad, paraphrase sources mechanically, or manufacture first-hand experience, reviews, citations, author credentials, data, or quotes.
- Set acceptance and verification. Specify a human fact/brand/legal review, rendered-page review, title/meta uniqueness and source-data check, link check, accessibility check, and a source-appropriate measurement plan. A visible answer or structured layout may improve clarity; it does not guarantee ranking, retrieval, citation, traffic, or conversion.
Content choices that need care
- Use direct answers where the reader asks a direct question, but retain conditions, dates, qualifications, and ownership of the fact.
- Make source attribution useful to readers; citations should support a real claim, not decorate a page or imitate an AI platform requirement.
- Prefer specific examples, methods, screenshots, original research, expert review, or transparent limits over generic “thought leadership.”
- Use internal links only to verified, useful destinations. Do not set link-count quotas or add irrelevant anchors.
- Treat title, H1, meta description, headings, lists, tables, alt text, and schema as reader-facing/technical choices with their own owners—not as universal ranking levers.
- Preserve locale meaning. A translation is not automatically a local-market page; request localized facts, legal wording, pricing/availability scope, and reviewer ownership where needed.
AI-search and platform boundaries
Google’s current AI guidance treats standard, crawlable, people-first content as the foundation and does not require special AI markup, chunking, or llms.txt. The owner-defined Markdown discovery profile is the suite delivery default; do not describe it as a Google inclusion requirement. Do not claim that an answer-first section, FAQ, schema, or bot access will make a system cite a page. Route platform-specific research to ai-search-research, direct-answer audits to seo-aeo, citation/entity evidence to seo-geo, and repeatable observations to ai-visibility-monitor.
Formal evidence handoff
When this work needs a cross-team, approval-ready plan, package evidence-bound findings as an immutable seo-findings.json bundle using the checked-out suite contract. Let <suite-root> mean ${CLAUDE_PLUGIN_ROOT} in Claude Code. In Codex, read .seo-suite-runtime.json beside this SKILL.md when present and use its suite_root value; otherwise use the absolute repository checkout. Keep every referenced capture/source below raw/, retain declined claims and limitations, and run python "<suite-root>/scripts/validate_seo_findings.py" validate-findings <bundle>/seo-findings.json --bundle <bundle>. Send only a passing bundle to seo-action-plan; otherwise label the handoff provisional.
Outputs
Return only the artifacts the evidence supports:
- Editorial audit: observations, evidence/limitations, prioritized opportunities, and unanswered questions.
- Content brief: reader task, claim ledger, outline, required evidence, locale/accessibility/CTA requirements, review gates, and acceptance criteria.
- Draft/rewrite options: clearly marked page copy plus complete title/meta candidates when in scope, with source notes and placeholders; never publish or represent it as approved.
- Action handoff: owner, dependencies, verification, rollback for potentially harmful edits, and the matching
seo-action-planaction ID when one exists.
Do not output a universal content score, minimum word-count mandate, keyword-density target, rigid readability target, or guaranteed AI-citation result.
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.

