#429429th of 455 in Skills, plugins and promptsFor finance and business, e-commerce, marketing and sales
agentic-seo-skill
SEO audit skill for Claude Code, Codex, Cursor and other coding agents
- Stars
- 1.1k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- May 2026
- Language
- Python
410 on 22 Apr 20261,050 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Installs as a skill or rule in nine agent IDEs, including Claude Code, Codex, Cursor, Windsurf, Copilot and Cline. It bundles 16 SEO sub-skills, 10 specialist agents and 88 Python scripts that collect crawl, robots, sitemap, schema and Core Web Vitals evidence. The LLM reasons over that evidence and writes FULL-AUDIT-REPORT.md and ACTION-PLAN.md. A GitHub repo SEO mode is also included.
Who it is for: Developers who want SEO audits run from their coding agent
Strengths
- Native install formats for nine tools, including Cursor MDC rules and Claude skill directories
- audit_runner.py writes JSON, HTML, FULL-AUDIT-REPORT.md and ACTION-PLAN.md in one command
- Findings carry Confirmed, Likely or Hypothesis labels under a fixed evidence rubric
- CI checks script inventory and flags reference files older than 90 days
Weaknesses
- Analysis quality depends on the host LLM; scripts only gather evidence
- Search Console features need credentials the user must supply
- Visual analysis needs a separate Playwright and Chromium install
- No standalone UI; used through an agent IDE or by running scripts directly
What it needs
- no GPU
- Needs Python 3, requests, beautifulsoup4, Playwright (optional)
- Models: Claude Code, Codex CLI, Cursor, Windsurf, GitHub Copilot
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |