Site audits report thousands of ‘errors’ and most of them don’t matter. This skill sorts the few that do, by impact on the pages that make money and by how much work the fix is.
What it does
Groups issues by type and site section, with URL counts
Scores each group by impact and effort, money pages first
Checks the usual suspects: noindex, canonicals, robots.txt, redirects, orphans
Lists what’s fine to leave, so nobody chases it
Try asking
“Here’s my Screaming Frog export. What do I fix first?”
“Search Console says 2,000 pages are ‘Crawled, currently not indexed’. Here’s the list. Triage it.”
Install it
Download the ZIP above.
Claude.ai: open Settings, go to Capabilities and upload it under Skills.
Claude Code: unzip it into ~/.claude/skills/ (all projects) or .claude/skills/ (one project).
The full instructions are below. It’s one Markdown file, so change anything you like.
Inside the skill
technical-seo-triage/SKILL.md
---
name: technical-seo-triage
description: Prioritise technical SEO issues from a crawl export (Screaming Frog, Sitebulb, Ahrefs or Semrush site audit) or a Search Console export. Use when someone shares an audit, a crawl CSV or a list of SEO errors and asks what to fix first.
---
# Technical SEO triage
Turn a long list of audit warnings into a short, ordered fix list. Most audit "errors" don't matter much; a few matter a lot.
## Inputs
- A crawl or audit export (CSV or pasted rows) and, if available, Search Console's Pages (indexing) report
- The site type (SaaS, ecommerce, publisher) and which sections make money
## Steps
1. **Group** issues by type and count affected URLs, split by site section (e.g. /blog/, /product/, /docs/).
2. **Score** each group:
- **Impact:** does it stop pages being crawled or indexed, waste crawl budget, or just look untidy? Weight issues on money pages higher.
- **Effort:** a template fix (one change, many URLs), a config change, or page-by-page work.
3. **Check the usual suspects first:**
- noindex or canonical mistakes on pages that should rank
- robots.txt blocking important sections, or AI search crawlers
- redirect chains and internal links pointing at redirects or 404s
- orphan pages with no internal links
- duplicate or parameter URLs being indexed
- slow or JavaScript-only rendering on key templates
- broken hreflang on multilingual sites
4. **Ignore with reasons:** list issues that don't need work (e.g. missing meta descriptions on paginated pages) so nobody chases them.
## Output format
```
## Fix first (blocks indexing or rankings)
| Issue | URLs | Section | Fix | Effort |
## Fix next (wastes crawl or link equity)
| … |
## Fine to leave
- issue: why it doesn't matter here
## How to check it worked
- what to re-crawl or watch in Search Console
```
## Rules
- Lead with what affects revenue pages.
- Prefer template-level fixes that clear many URLs at once.
- Don't call something critical because the tool coloured it red.
Questions
How do I install it in Claude.ai?
Download the ZIP, then in Claude.ai open Settings, go to Capabilities and upload it under Skills. Claude picks it up when your request matches what the skill does.
How do I use it in Claude Code?
Unzip it into ~/.claude/skills/ for every project, or into .claude/skills/ inside one project. The folder name stays the same as the skill's name.
Can I edit it?
Yes, it's a plain Markdown file (SKILL.md). Change the steps, the output format or the rules to match how your team works.