Agentic SEO Skill
SEO audits for sites, articles and GitHub repos: topic sub-skills, evidence-collecting scripts and a fix plan
Install
curl -fsSL https://raw.githubusercontent.com/Bhanunamikaze/Agentic-SEO-Skill/main/install.sh | bash -s -- --online --target claudeWithout --target it installs into every supported agent. Add --install-deps for Python dependencies.
This is third-party code. Review the repository files before installing.
What it does
The seo skill parses the request and routes it to a sub-skill: full site audit, single page review, technical SEO, content and E-E-A-T, Schema.org markup, sitemaps, images, hreflang, GEO and AEO for AI answers, links and GitHub repository SEO. Python scripts collect evidence: they fetch pages and check robots.txt, sitemaps, indexability, Core Web Vitals and JSON-LD. Each finding gets evidence, impact, a fix and a confidence label. A full audit produces FULL-AUDIT-REPORT.md and ACTION-PLAN.md, plus an optional HTML report.
Who it is for. For SEO specialists, marketers and developers who want an evidence-backed site audit inside their agent.
Good fit when
- You need a full technical and content audit of a site
- You need to validate Schema.org markup or hreflang
- You want a site ready to be cited in AI answers
- You want to improve a GitHub repository's discoverability
Not a fit when
- You need Yandex Webmaster or Metrica data: the skill is Google-oriented
- You need rank tracking or keyword volumes
Example request
Run an SEO audit of example.com and build a prioritized fix planLimitations
Recommendations follow Google's rules. Scripts need Python with requests and beautifulsoup4, and visual analysis needs Playwright with Chromium. PageSpeed checks call the Google API. A full audit crawls many pages and takes time.
How to disable. Delete the seo folder from ~/.claude/skills/ or ~/.codex/skills/; for Cursor and Windsurf remove the generated rule files in the project.
Security check
- Runs Python scripts and crawls site pages
- Installs via a script downloaded from the internet
README in short
The README lists supported agents with install paths, sub-skills, specialist agents and key scripts. It describes the audit flow: evidence collection, model analysis against a rubric, confidence labels and an action plan. Installation uses install.sh or install.ps1 with a --target flag, with an option to download and review the script first. MIT licensed.
SKILL.md
--- name: seo description: > Deterministic LLM-first SEO audits for websites, blog posts, and GitHub repositories. Use this when the user asks to "perform SEO analysis", "run SEO audit", "analyze SEO", "check technical SEO", "review schema", "Core Web Vitals", "E-E-A-T", "hreflang", "GEO", "AEO", or GitHub repository SEO optimization. For full/page/repo audits, run bundled scripts for evidence and return prioritized, confidence-labeled fixes. --- # SEO Skill (Agentic / Claude / Codex) LLM-first SEO analysis skill with 16 specialized sub-skills, 10 specialist agents, and 89 scripts for website, blog, and GitHub repository optimization. ## Deterministic Trigger Mapping For prompt reliability in Codex/agent IDEs, map common user wording to a fixed workflow: - If user says `perform seo analysis on <url>` (or similar generic SEO request with a URL), treat it as a **single-URL full audit**. - If no explicit sub-skill is specified, run the full/page audit path with **LLM-first reasoning** and script-backed evidence. - For full/page audits, always produce: - `FULL-AUDIT-REPORT.md` (detailed findings) - `ACTION-PLAN.md` (prioritized fixes) - If `generate_report.py` is run, also return the saved HTML path (for example `SEO-REPORT.html`). ## Available Commands | Command | Sub-Skill | Description | |---------|-----------|-------------| | `seo audit <url>` | [seo-audit](resources/skills/seo-audit.md) | Full website audit with scoring | | `seo page <url>` | [seo-page](resources/skills/seo-page.md) | Deep single-page analysis | | `seo technical <url>` | [seo-technical](resources/skills/seo-technical.md) | Technical SEO checks | | `seo content <url>` | [seo-content](resources/skills/seo-content.md) | Content quality & E-E-A-T | | `seo schema <url>` | [seo-schema](resources/skills/seo-schema.md) | Schema detection/validation/generation |
FAQ
Do I need to remember sub-skill commands?
No, the skill picks the right sub-skill from how the request is phrased.
Which agents are supported?
Claude Code, Codex, Antigravity, Cursor, Windsurf, Continue, GitHub Copilot and Cline; the installer writes native files for each.
Related
A Claude Code plugin for SEO audits: technical SEO, E-E-A-T, schema, local and AI search via parallel subagents
A Claude Code skill set for auditing sites for AI search: citability, AI crawler access, llms.txt, schema and reports
The experimental official Google Analytics 4 MCP server: reports, funnels and realtime data on request
Google Search Console MCP
Google Search Console MCP Server for SEOs
An MCP server for Google Search Console: queries and pages with clicks and positions, URL indexing checks, sitemaps and ready SEO skills