How do I install the SEO Technical skill?

Run npx skillmds@latest add karvedconcepts/seo-technical in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is SEO Technical safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with SEO Technical?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is SEO Technical free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published SEO Technical?

karvedconcepts (@karvedconcepts) published this skill. Their other Agent Skills are listed on their SkillMD profile.

SEO Technical by karvedconcepts — Agent Skill

Name: SEO Technical
Author: karvedconcepts

SEO Technical

Shopify technical SEO audit sub-skill. Checks crawl health, HTTPS status, redirects, canonical tags, sitemap.xml, and robots.txt. Use when user runs /seo technical or when seo-audit delegates technical checks.

File contents

SEO Technical Audit

Technical SEO sub-skill for Shopify stores. Checks crawl health, HTTPS enforcement, redirect chains, canonical tags, sitemap validity, and robots.txt configuration. Category weight: Technical = 25% (0.25) of overall SEO Health Score.

Quick Reference

Command	What it does
`/seo technical <url>`	Run technical SEO checks against a Shopify store
(via seo-audit)	seo-audit spawns audit-technical agent directly — this sub-skill is not used

Context Intake

This skill is invoked directly via /seo technical <url>.

When invoked directly:

If store URL not provided, read ~/.claude/skills/seo/profiles/karved.json and use preset
Run python3 ~/.claude/skills/seo/scripts/crawl_store.py <url> to generate crawl data before proceeding
Save output as seo-audit-crawl.json in the current directory
Then proceed to Execution Logic

Note: When invoked by seo-audit, this sub-skill is NOT used — seo-audit spawns the audit-technical agent directly.

Execution Logic

If invoked directly (not from seo-audit): a. If store URL not provided, read ~/.claude/skills/seo/profiles/karved.json and use preset b. Run python3 ~/.claude/skills/seo/scripts/crawl_store.py <url> to generate seo-audit-crawl.json
Spawn agent audit-technical via Task tool with prompt: "Run technical SEO audit on {store_url}. Crawl data at {cwd}/seo-audit-crawl.json"
Agent writes seo-technical-findings.md — present results to user

All check definitions, scoring logic, and output format are defined in the agent. If invoked by seo-audit, this sub-skill is NOT used — seo-audit spawns the agent directly.

Quality Gates

This skill inherits all quality gates from seo/SKILL.md. Do NOT redefine or soften them. The audit-technical agent applies severity levels locked by the quality gates.

Reference Files

Load these on-demand as needed — do NOT load all at startup.

Path resolution: All references are installed at ~/.claude/skills/seo/references/.

references/scoring-system.md — Weighted scoring algorithm, severity multipliers (Critical=5.0, High=3.0, Medium=1.5, Low=0.5), grade thresholds
references/shopify-seo.md — Shopify duplicate content patterns, canonical_url Liquid fix, robots.txt/sitemap behavior, collection filter URL handling

The agent loads its own references during execution.

---name: seo-technicaldescription: Shopify technical SEO audit sub-skill. Checks crawl health, HTTPS status, redirects, canonical tags, sitemap.xml, and robots.txt. Use when user runs /seo technical or when seo-audit delegates technical checks.---# SEO Technical AuditTechnical SEO sub-skill for Shopify stores. Checks crawl health, HTTPS enforcement,redirect chains, canonical tags, sitemap validity, and robots.txt configuration.Category weight: Technical = 25% (0.25) of overall SEO Health Score.## Quick Reference| Command | What it does ||---------|-------------|| `/seo technical <url>` | Run technical SEO checks against a Shopify store || (via seo-audit) | seo-audit spawns audit-technical agent directly — this sub-skill is not used |## Context IntakeThis skill is invoked directly via `/seo technical <url>`.**When invoked directly:**- If store URL not provided, read `~/.claude/skills/seo/profiles/karved.json` and use preset- Run `python3 ~/.claude/skills/seo/scripts/crawl_store.py <url>` to generate crawl data before proceeding- Save output as `seo-audit-crawl.json` in the current directory- Then proceed to Execution Logic**Note:** When invoked by seo-audit, this sub-skill is NOT used — seo-audit spawns the audit-technical agent directly.## Execution Logic1. If invoked directly (not from seo-audit): a. If store URL not provided, read `~/.claude/skills/seo/profiles/karved.json` and use preset b. Run `python3 ~/.claude/skills/seo/scripts/crawl_store.py <url>` to generate `seo-audit-crawl.json`2. Spawn agent `audit-technical` via Task tool with prompt: "Run technical SEO audit on {store_url}. Crawl data at {cwd}/seo-audit-crawl.json"3. Agent writes `seo-technical-findings.md` — present results to userAll check definitions, scoring logic, and output format are defined in the agent.If invoked by seo-audit, this sub-skill is NOT used — seo-audit spawns the agent directly.## Quality GatesThis skill inherits all quality gates from `seo/SKILL.md`. Do NOT redefine or soften them. The audit-technical agent applies severity levels locked by the quality gates.## Reference FilesLoad these on-demand as needed — do NOT load all at startup.**Path resolution:** All references are installed at `~/.claude/skills/seo/references/`.- `references/scoring-system.md` — Weighted scoring algorithm, severity multipliers (Critical=5.0, High=3.0, Medium=1.5, Low=0.5), grade thresholds- `references/shopify-seo.md` — Shopify duplicate content patterns, canonical_url Liquid fix, robots.txt/sitemap behavior, collection filter URL handlingThe agent loads its own references during execution.

Frequently asked questions