claude-seo-geo
AGENTS.md18 starsChanged 9 days agoMITView on GitHub
Every skill in this repository is plain markdown that follows the open Agent Skills format (https://agentskills.io). Nothing here depends on Claude Code internals, so the same files work in any agent that can read instructions from disk. Install as a plugin (recommended): Or copy skills manually:
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository27 other files it gives its agents.
- geo-trackingSkill
- geo-visibilitySkill
- seo-ai-site-buildersSkill
- seo-audit-pdfSkill
- seo-backlinksSkill
- seo-competitor-analysisSkill
- seo-content-blogSkill
- seo-content-collection-pageSkill
- seo-content-comparison-hubSkill
- seo-content-comparison-pageSkill
- seo-content-data-studySkill
- seo-content-homepageSkill
- seo-content-product-pageSkill
- seo-content-service-pageSkill
- seo-geo-auditSkill
- seo-internal-linkingSkill
- seo-keyword-researchSkill
- seo-localSkill
- seo-page-sectionsSkill
- seo-schema-markupSkill
- seo-sitemapSkill
- seo-technicalSkill
- seo-traffic-dropSkill
- social-amplificationSkill
- youtube-descriptionSkill
- youtube-thumbnailSkill
- youtube-titleSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 3
Every skill in this repository is plain markdown that follows the open Agent Skills format (https://agentskills.io).
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Using these skills outside Claude Code
Every skill in this repository is plain markdown that follows the open Agent Skills format (https://agentskills.io). Nothing here depends on Claude Code internals, so the same files work in any agent that can read instructions from disk.
Claude Code
Install as a plugin (recommended):
/plugin marketplace add Thibaultbm/claude-seo-geo
/plugin install claude-seo-geo@sorankOr copy skills manually:
git clone --depth 1 https://github.com/Thibaultbm/claude-seo-geo.git
cp -r claude-seo-geo/skills/* ~/.claude/skills/Cursor, Codex, Gemini CLI, Cline, Aider and others
- Clone the repository somewhere stable.
- Point your agent at the skill you need: paste the relevant
SKILL.mdinto context, or reference its path in your rules file (.cursorrules,AGENTS.md,GEMINI.md, etc). - The
references/files inside each skill are meant to be loaded on demand: load them when the SKILL.md says so, not upfront. - The executables in the repository are
skills/seo-geo-audit/scripts/seo_audit.py,skills/seo-geo-audit/scripts/page_benchmark.py,skills/seo-page-sections/scripts/section_audit.py,skills/seo-internal-linking/scripts/site_crawl.py,skills/seo-traffic-drop/scripts/content_decay.py,skills/seo-ai-site-builders/scripts/render_check.py,skills/seo-traffic-drop/scripts/gsc_diff.py,skills/seo-audit-pdf/scripts/render_pdf.py,skills/seo-sitemap/scripts/sitemap_audit.py,skills/seo-competitor-analysis/scripts/competitor_sitemaps.py,skills/seo-content-data-study/scripts/data_study.py,skills/seo-content-comparison-hub/scripts/hub_check.py, andskills/youtube-description/scripts/youtube_check.py. All are pure Python standard library (Python 3.9+), no packages to install, no API keys.
Skill map
| Skill | Use it for |
| seo-traffic-drop | Diagnose a traffic or ranking loss: is it real, when did it start, where is it, what caused it |
| seo-geo-audit | Full site audit (SEO + AI visibility), prioritized action plan |
| seo-audit-pdf | The audit as a client-ready PDF (fixed layout, nothing cut across pages, no dates or delays) |
| seo-technical | Crawlability, indexation, speed, JS rendering, AI crawler access |
| seo-sitemap | Sitemaps clean for robots and elegant for people: pretty-printed raw XML (no stylesheet), sitemap index, honest lastmod |
| seo-competitor-analysis | Market analysis from every competitor sitemap: page models, topics and pace you lack (asks for 5 competitors first, or finds them) |
| seo-content-data-study | Data studies, statistics and case study pages from anonymized proprietary data, with charts |
| seo-keyword-research | Keywords, search intent, AI prompt research |
| seo-content-blog | Blog articles that rank and get cited, plus the article and blog hub templates |
| seo-content-product-page | E-commerce product pages |
| seo-content-homepage | Homepage and flagship offer (sales) page |
| seo-content-service-page | Service and landing pages |
| seo-content-collection-page | E-commerce category and collection pages |
| seo-content-comparison-page | Comparison, alternatives, best-for and customer segment pages |
| seo-content-comparison-hub | The ideal structure of a "best {category}" ranking hub, section by section |
| seo-page-sections | Which sections a page is missing, and the content to fill each gap |
| seo-ai-site-builders | Sites built by AI generators (Lovable, Base44, Bolt, v0, Bubble and others): turn the JavaScript app into served HTML so it can be indexed and cited |
| seo-internal-linking | Internal links, silos, orphan pages |
| seo-schema-markup | Structured data that still matters in 2026 |
| seo-backlinks | Link building, ninja linking, brand mentions |
| seo-local | Google Business Profile, reviews, local pages |
| social-amplification | Repurpose and distribute content to drive branded search and feed AI citation surfaces |
| youtube-title | YouTube titles that are found and clicked, paired with the thumbnail hook |
| youtube-description | YouTube descriptions and chapters written from the transcript |
| youtube-thumbnail | YouTube thumbnails readable at phone size, in the brand's colors |
| geo-visibility | Getting cited by ChatGPT, Perplexity, AI Overviews |
| geo-tracking | Measuring AI traffic, citations and share of voice |
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.