seo
An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: analysis, seo, strategy, validation, web.
What it does
Comprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability, indexability, Core Web Vitals with INP), schema markup, content quality (E-E-A-T), image optimization, sitemap analysis, and GEO for AI Overviews/ChatGPT/Perplexity. Industry detection for SaaS, e-commerce, local, publishers, agencies. Triggers on: SEO, audit, schema, Core Web Vitals, sitemap, E-E-A-T, AI Overviews, GEO, technical SEO, content quality, page speed.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add AgriciDaniel/claude-seo --skill seoOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/AgriciDaniel/claude-seo
cp -r claude-seo/skills/seo ~/.claude/skills/seoSafety box score
Grade C, moderate risk: 44 of 100 risk points, rated 2026-10-05. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a live SEO analysis orchestrator, not a passive doc pack: it runs bundled scripts, can invoke Lighthouse, and reaches out to target sites and multiple third-party SEO services. The main risks are external network access, credential/API-key use, and local setup writes under the user’s home directory; it does not appear to contain prompt-injection style hidden instructions or destructive actions.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It explicitly runs code via `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run <script.py>` and also references `npx lighthouse URL --output json --output-path report.json` in `references/cwv-thresholds.md`. |
| Network access | 2 (moderate) | The skill fetches live websites and calls external services such as DataForSEO, Google APIs, Overpass, Geoapify, and optional Firecrawl, so analysis data leaves the machine. |
| Filesystem reach | 2 (moderate) | It writes to home-directory locations such as `~/.cache/claude-seo/commoncrawl/` and refers to the installed launcher at `$HOME/.claude/skills/seo/scripts/claude-seo`, plus `/seo setup` refreshes a local runtime and Chromium. |
| Secrets & credentials | 2 (moderate) | It checks and can use API credentials for Google, Matomo, Moz, Bing, and DataForSEO; `references/cwv-thresholds.md` even shows `curl -H "X-Goog-Api-Key: $GOOGLE_API_KEY"`. |
| Privilege & persistence | 1 (low) | `/seo setup` creates or refreshes an isolated Python runtime and Chromium, but the skill says not to use global/user package installation and does not require sudo or services. |
| Instruction hijack surface | 0 (none) | I did not find hidden text, remote-instruction fetching, or directives to bypass confirmations; the instructions are local workflow constraints like `do not improvise a pip install`. |
| Irreversible actions | 1 (low) | It can automatically orchestrate parallel subagents, generate PDF reports, and capture drift baselines, but it does not publish, pay, deploy, or delete anything externally. |
| Transparency | 1 (low) | The included files are readable markdown, but the skill references optional extension installers and scripts that are not present in the provided file set, so part of the runtime surface is not reviewable here. |
Before installing
- Read `SKILL.md`’s setup and command sections to confirm you want live web/API access and local Chromium/runtime changes.
- Check whether you are comfortable exposing your SEO API credentials or paid credits to the skill (Google, DataForSEO, Moz, Bing, Matomo).
- If you plan to enable optional extensions, inspect their `install.sh`/`install.ps1` files separately before running them.
- Test `/seo doctor` or `/seo setup` in a scratch account first to see what it writes under your home directory.
Rated 2026-10-05 by an automated review of 19 files from the skill's repository.
Source
- Repository
- AgriciDaniel/claude-seo (all skills from this repository)
- Path
- skills/seo/SKILL.md
- Branch
- main
- Collection
- claude-seo
- Updated
- 2026-09-21
Related skills
- seo-page — Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance.
- seo-cluster — SERP-based semantic topic clustering for content architecture planning.
- seo-content — Content quality and E-E-A-T analysis with AI citation readiness assessment.
- seo-plan — Strategic SEO planning for new or existing websites. Industry-specific templates, competitive analysis, content strategy, and implementation roadmap.
- seo-sitemap — Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure.
- seo-sxo — Search Experience Optimization: reads Google SERPs backwards to detect page-type mismatches, derives user stories from search intent signals.