Skills Explorer Add Skills

seo-technical

An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: analysis, security, seo, troubleshooting, validation.

What it does

Technical SEO audit across 9 categories: crawlability, indexability, security, URL structure, mobile, Core Web Vitals, structured data, JavaScript rendering, and IndexNow protocol. Use when user says "technical SEO", "crawl issues", "robots.txt", "Core Web Vitals", "site speed", or "security headers".

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add AgriciDaniel/claude-seo --skill seo-technical

Or 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-technical ~/.claude/skills/seo-technical

Safety box score

Grade B, low risk: 23 of 100 risk points, rated 2026-10-18. 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 skill runs a technical SEO audit by invoking bundled scripts against a target URL, with optional browser rendering and optional Google/DataForSEO integrations. The main exposure is network reach: it can crawl public or allowlisted private hosts and send audit data to external services; it does not appear to modify files or require elevated privileges.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)It repeatedly calls a bundled runner, `${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo`, with subcommands like `sitemap_discovery.py`, `agentic_check.py`, and `render_page.py`, so it executes shipped code and may launch Chromium during the audit.
Network access2 (moderate)The skill audits arbitrary `<url>` targets, can follow discovered URLs, and optionally uses Google API/CrUX/GSC or DataForSEO integrations, so it sends requests off-box and can reach additional sites.
Filesystem reach0 (none)The documented behavior is read-only auditing of URLs; there are no commands to edit, delete, or traverse local files outside the project.
Secrets & credentials1 (low)Optional `pagespeed_check.py`, `crux_history.py`, and `gsc_inspect.py` integrations can use the user's configured Google/Search Console credentials, but the skill does not ask for passwords or key files directly.
Privilege & persistence0 (none)No `sudo`, global install, service registration, or shell/OS setting changes are requested.
Instruction hijack surface0 (none)The file gives SEO guidance and tool usage, but it does not tell the agent to ignore its rules, skip confirmations, or follow remote instructions.
Irreversible actions0 (none)This is an audit-only skill: it reports findings and recommendations, but does not post, deploy, pay, book, merge, or delete on the user's behalf.
Transparency1 (low)The core implementation is a native wrapper referenced as `${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo`, and its actual code is not visible in the provided files.

Before installing

Rated 2026-10-18 by an automated review of 2 files from the skill's repository.

Source

Repository
AgriciDaniel/claude-seo (all skills from this repository)
Path
skills/seo-technical/SKILL.md
Branch
main
Collection
claude-seo
Updated
2026-09-21