Claude Skill

solo-seo-audit

Use when "check SEO", "audit this page", "SEO score", "check meta tags", "SERP position", or need website SEO health check. Do NOT use for landing content (/landing-gen) or social media posts (/content-gen).

LLM Mart · 0 points · 4 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download fortunto2-solo-factory-skills_seo-audit-05ec009.zip · 3 KB
fortunto2/solo-factory 18 3 forks MIT Updated 11d ago
Part of fortunto2/solo-factory — 43 skills

Install

skills CLI npx skills add https://github.com/fortunto2/solo-factory/tree/main/skills/seo-audit
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install fortunto2-solo-factory@llmmart
Git git clone https://github.com/fortunto2/solo-factory.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole fortunto2/solo-factory collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

/seo-audit

SEO health check for any URL or project landing page. Fetches the page, analyzes meta tags, OG, JSON-LD, sitemap, robots.txt, checks SERP positions for target keywords, and outputs a scored report.

seo-cli (use if available)

Dedicated SEO CLI — repo: https://github.com/fortunto2/seo-cli

# Install (one-time)
git clone https://github.com/fortunto2/seo-cli.git ~/startups/shared/seo-cli
cd ~/startups/shared/seo-cli && uv venv && uv pip install -e .
cp config.example.yaml config.yaml  # add credentials (GSC, Bing, Yandex, IndexNow)

# Detect seo-cli
python ~/startups/shared/seo-cli/cli.py --help 2>/dev/null

If available, prefer seo-cli commands over manual WebFetch:

  • python ~/startups/shared/seo-cli/cli.py audit <url> — deep page audit (meta, OG, JSON-LD, keywords, readability)
  • python ~/startups/shared/seo-cli/cli.py status — dashboard for all registered sites
  • python ~/startups/shared/seo-cli/cli.py analytics <site> — GSC data (queries, impressions, CTR)
  • python ~/startups/shared/seo-cli/cli.py monitor <site> — position tracking with snapshots
  • python ~/startups/shared/seo-cli/cli.py reindex <url> — instant reindex via Google Indexing API + IndexNow
  • python ~/startups/shared/seo-cli/cli.py competitors <keyword> — SERP + competitor analysis
  • python ~/startups/shared/seo-cli/cli.py launch <site> — full new site promotion workflow

If seo-cli is not available, fall back to WebFetch-based audit below.

MCP Tools (use if available)

  • web_search(query, engines, include_raw_content) — SERP position check, competitor analysis
  • project_info(name) — get project URL if auditing by project name

If MCP tools are not available, use Claude WebSearch/WebFetch as fallback.

Steps

  1. Parse target from $ARGUMENTS.

    • If URL (starts with http): use directly.
    • If project name: look up URL from project README, CLAUDE.md, or docs/prd.md.
    • If empty: ask via AskUserQuestion — "Which URL or project to audit?"

  2. Fetch the page via WebFetch. Extract:

    • <title> tag (length check: 50-60 chars ideal)
    • <meta name="description"> (length check: 150-160 chars ideal)
    • Open Graph tags: og:title, og:description, og:image, og:url, og:type
    • Twitter Card tags: twitter:card, twitter:title, twitter:image
    • JSON-LD structured data (<script type="application/ld+json">)
    • <link rel="canonical"> — canonical URL
    • <html lang="..."> — language tag
    • <link rel="alternate" hreflang="..."> — i18n tags
    • Heading structure: H1 count (should be exactly 1), H2-H3 hierarchy

  3. Check infrastructure files:

    • Fetch {origin}/sitemap.xml — exists? Valid XML? Page count?
    • Fetch {origin}/robots.txt — exists? Disallow rules? Sitemap reference?
    • Fetch {origin}/favicon.ico — exists?

  4. Forced reasoning — assess before scoring: Write out before proceeding:

    • What's present: [list of found elements]
    • What's missing: [list of absent elements]
    • Critical issues: [anything that blocks indexing or sharing]

  5. SERP position check — for 3-5 keywords:

    • Extract keywords from page title + meta description + H1.
    • For each keyword, search via MCP web_search(query="{keyword}") or WebSearch.
    • Record: position of target URL in results (1-10, or "not found").
    • Record: top 3 competitors for each keyword.

  6. Score calculation (0-100):

    Check Max Points Criteria
    Title tag 10 Exists, 50-60 chars, contains primary keyword
    Meta description 10 Exists, 150-160 chars, compelling
    OG tags 10 og:title, og:description, og:image all present
    JSON-LD 10 Valid structured data present
    Canonical 5 Present and correct
    Sitemap 10 Exists, valid, referenced in robots.txt
    Robots.txt 5 Exists, no overly broad Disallow
    H1 structure 5 Exactly one H1, descriptive
    HTTPS 5 Site uses HTTPS
    Mobile meta 5 Viewport tag present
    Language 5 lang attribute on <html>
    Favicon 5 Exists
    SERP presence 15 Found in top 10 for target keywords

  7. Write report to docs/seo-audit.md (in project context) or print to console:

    # SEO Audit: {URL}

**Date:** {YYYY-MM-DD}
**Score:** {N}/100

## Summary
{2-3 sentence overview of SEO health}

## Checks

| Check | Status | Score | Details |
|-------|--------|-------|---------|
| Title | pass/fail | X/10 | "{actual title}" (N chars) |
| ... | ... | ... | ... |

## SERP Positions

| Keyword | Position | Top Competitors |
|---------|----------|----------------|
| {kw} | #N or N/A | competitor1, competitor2, competitor3 |

## Critical Issues
- {issue with fix recommendation}

## Recommendations (Top 3)
1. {highest impact fix}
2. {second priority}
3. {third priority}

  8. Output summary — print score and top 3 recommendations.

Notes

  • Score is relative — 80+ is good for a landing page, 90+ is excellent
  • SERP checks are approximations (not real-time ranking data)
  • Run periodically after content changes or before launch

Gotchas

  1. SPA without SSR scores zero — if the page is client-rendered only (React SPA, no Next.js SSR), search engines see an empty <div id="root">. Check view-source: to verify HTML contains actual content.
  2. Sitemap in robots.txt is not optional — Google finds sitemaps from robots.txt Sitemap: directive. Without it, indexing depends on internal link crawling which is slow for new sites.
  3. JSON-LD errors are silent — malformed JSON-LD doesn't break the page but Google ignores it completely. Validate with https://search.google.com/test/rich-results before shipping.
  4. Multiple H1 tags confuse crawlers — many UI frameworks render component titles as H1. Audit the actual DOM — there should be exactly one H1 per page. Use H2-H3 for section headings.
  5. Core Web Vitals affect ranking — LCP (Largest Contentful Paint) < 2.5s, FID (First Input Delay) < 100ms, CLS (Cumulative Layout Shift) < 0.1. Check via npx lighthouse {url} --output=json if lighthouse is available.

Common Issues

Page fetch fails

Cause: URL is behind authentication, CORS, or returns non-HTML. Fix: Ensure the URL is publicly accessible. For SPAs, check if content is server-rendered.

SERP positions show "not found"

Cause: Site is new or not indexed by search engines. Fix: This is expected for new sites. Submit sitemap to Google Search Console and re-audit in 2-4 weeks.

Low score despite good content

Cause: Missing infrastructure files (sitemap.xml, robots.txt, JSON-LD). Fix: These are the highest-impact fixes. Generate sitemap, add robots.txt with sitemap reference, and add JSON-LD structured data.

Files (solo-factory)
  • SKILL.md 7.3 KB 
    ---
name: solo-seo-audit
description: Use when "check SEO", "audit this page", "SEO score", "check meta tags", "SERP position", or need website SEO health check. Do NOT use for landing content (/landing-gen) or social media posts (/content-gen).
license: MIT
metadata:
  author: fortunto2
  version: "1.1.1"
  openclaw:
    emoji: "📊"
allowed-tools: Read, Grep, Bash, Glob, Write, WebSearch, WebFetch, AskUserQuestion, mcp__searxng__web_search, mcp__solograph__project_info
argument-hint: "<url or project-name>"
---

# /seo-audit

SEO health check for any URL or project landing page. Fetches the page, analyzes meta tags, OG, JSON-LD, sitemap, robots.txt, checks SERP positions for target keywords, and outputs a scored report.

## seo-cli (use if available)

Dedicated SEO CLI — repo: `https://github.com/fortunto2/seo-cli`

```bash
# Install (one-time)
git clone https://github.com/fortunto2/seo-cli.git ~/startups/shared/seo-cli
cd ~/startups/shared/seo-cli && uv venv && uv pip install -e .
cp config.example.yaml config.yaml  # add credentials (GSC, Bing, Yandex, IndexNow)
```

```bash
# Detect seo-cli
python ~/startups/shared/seo-cli/cli.py --help 2>/dev/null
```

If available, prefer `seo-cli` commands over manual WebFetch:
- `python ~/startups/shared/seo-cli/cli.py audit <url>` — deep page audit (meta, OG, JSON-LD, keywords, readability)
- `python ~/startups/shared/seo-cli/cli.py status` — dashboard for all registered sites
- `python ~/startups/shared/seo-cli/cli.py analytics <site>` — GSC data (queries, impressions, CTR)
- `python ~/startups/shared/seo-cli/cli.py monitor <site>` — position tracking with snapshots
- `python ~/startups/shared/seo-cli/cli.py reindex <url>` — instant reindex via Google Indexing API + IndexNow
- `python ~/startups/shared/seo-cli/cli.py competitors <keyword>` — SERP + competitor analysis
- `python ~/startups/shared/seo-cli/cli.py launch <site>` — full new site promotion workflow

If seo-cli is not available, fall back to WebFetch-based audit below.

## MCP Tools (use if available)

- `web_search(query, engines, include_raw_content)` — SERP position check, competitor analysis
- `project_info(name)` — get project URL if auditing by project name

If MCP tools are not available, use Claude WebSearch/WebFetch as fallback.

## Steps

1. **Parse target** from `$ARGUMENTS`.
   - If URL (starts with `http`): use directly.
   - If project name: look up URL from project README, CLAUDE.md, or `docs/prd.md`.
   - If empty: ask via AskUserQuestion — "Which URL or project to audit?"

2. **Fetch the page** via WebFetch. Extract:
   - `<title>` tag (length check: 50-60 chars ideal)
   - `<meta name="description">` (length check: 150-160 chars ideal)
   - Open Graph tags: `og:title`, `og:description`, `og:image`, `og:url`, `og:type`
   - Twitter Card tags: `twitter:card`, `twitter:title`, `twitter:image`
   - JSON-LD structured data (`<script type="application/ld+json">`)
   - `<link rel="canonical">` — canonical URL
   - `<html lang="...">` — language tag
   - `<link rel="alternate" hreflang="...">` — i18n tags
   - Heading structure: H1 count (should be exactly 1), H2-H3 hierarchy

3. **Check infrastructure files:**
   - Fetch `{origin}/sitemap.xml` — exists? Valid XML? Page count?
   - Fetch `{origin}/robots.txt` — exists? Disallow rules? Sitemap reference?
   - Fetch `{origin}/favicon.ico` — exists?

4. **Forced reasoning — assess before scoring:**
   Write out before proceeding:
   - **What's present:** [list of found elements]
   - **What's missing:** [list of absent elements]
   - **Critical issues:** [anything that blocks indexing or sharing]

5. **SERP position check** — for 3-5 keywords:
   - Extract keywords from page title + meta description + H1.
   - For each keyword, search via MCP `web_search(query="{keyword}")` or WebSearch.
   - Record: position of target URL in results (1-10, or "not found").
   - Record: top 3 competitors for each keyword.

6. **Score calculation** (0-100):

   | Check | Max Points | Criteria |
   |-------|-----------|----------|
   | Title tag | 10 | Exists, 50-60 chars, contains primary keyword |
   | Meta description | 10 | Exists, 150-160 chars, compelling |
   | OG tags | 10 | og:title, og:description, og:image all present |
   | JSON-LD | 10 | Valid structured data present |
   | Canonical | 5 | Present and correct |
   | Sitemap | 10 | Exists, valid, referenced in robots.txt |
   | Robots.txt | 5 | Exists, no overly broad Disallow |
   | H1 structure | 5 | Exactly one H1, descriptive |
   | HTTPS | 5 | Site uses HTTPS |
   | Mobile meta | 5 | Viewport tag present |
   | Language | 5 | `lang` attribute on `<html>` |
   | Favicon | 5 | Exists |
   | SERP presence | 15 | Found in top 10 for target keywords |

7. **Write report** to `docs/seo-audit.md` (in project context) or print to console:

   ```markdown
   # SEO Audit: {URL}

   **Date:** {YYYY-MM-DD}
   **Score:** {N}/100

   ## Summary
   {2-3 sentence overview of SEO health}

   ## Checks

   | Check | Status | Score | Details |
   |-------|--------|-------|---------|
   | Title | pass/fail | X/10 | "{actual title}" (N chars) |
   | ... | ... | ... | ... |

   ## SERP Positions

   | Keyword | Position | Top Competitors |
   |---------|----------|----------------|
   | {kw} | #N or N/A | competitor1, competitor2, competitor3 |

   ## Critical Issues
   - {issue with fix recommendation}

   ## Recommendations (Top 3)
   1. {highest impact fix}
   2. {second priority}
   3. {third priority}
   ```

8. **Output summary** — print score and top 3 recommendations.

## Notes

- Score is relative — 80+ is good for a landing page, 90+ is excellent
- SERP checks are approximations (not real-time ranking data)
- Run periodically after content changes or before launch

## Gotchas

1. **SPA without SSR scores zero** — if the page is client-rendered only (React SPA, no Next.js SSR), search engines see an empty `<div id="root">`. Check `view-source:` to verify HTML contains actual content.
2. **Sitemap in robots.txt is not optional** — Google finds sitemaps from robots.txt `Sitemap:` directive. Without it, indexing depends on internal link crawling which is slow for new sites.
3. **JSON-LD errors are silent** — malformed JSON-LD doesn't break the page but Google ignores it completely. Validate with https://search.google.com/test/rich-results before shipping.
4. **Multiple H1 tags confuse crawlers** — many UI frameworks render component titles as H1. Audit the actual DOM — there should be exactly one H1 per page. Use H2-H3 for section headings.
5. **Core Web Vitals affect ranking** — LCP (Largest Contentful Paint) < 2.5s, FID (First Input Delay) < 100ms, CLS (Cumulative Layout Shift) < 0.1. Check via `npx lighthouse {url} --output=json` if lighthouse is available.

## Common Issues

### Page fetch fails
**Cause:** URL is behind authentication, CORS, or returns non-HTML.
**Fix:** Ensure the URL is publicly accessible. For SPAs, check if content is server-rendered.

### SERP positions show "not found"
**Cause:** Site is new or not indexed by search engines.
**Fix:** This is expected for new sites. Submit sitemap to Google Search Console and re-audit in 2-4 weeks.

### Low score despite good content
**Cause:** Missing infrastructure files (sitemap.xml, robots.txt, JSON-LD).
**Fix:** These are the highest-impact fixes. Generate sitemap, add robots.txt with sitemap reference, and add JSON-LD structured data.

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related

Claude Prompt
Tighten-my-prose editing prompt
Claude Skill
Adversarial code-review skill for Claude
Claude Workflow
Deep-research workflow (fan-out + verify)
Claude Skill
Conventional-commit writer for Claude