Site audit skill

Audit a website's content, structure, SEO health, and technical setup through SandBase.

by sandbaseai·Apache-2.0 license·★ 203 Stars on the repo·GitHub ↗

Use now

Inside this skill

SKILL.md · the author's own words
# Site Audit

Comprehensive website auditing through SandBase. Crawl sites, analyze content, check SEO fundamentals, and assess structure. Read [the API…

## Call SandBase capabilities

Use the capability identifiers below as discovery hints, not MCP tool names. Find the matching endpoint with `sandbase_discover(q: "<provid…

## Operating principles

- Start with site structure before diving into page-level analysis.
- Prioritize issues by impact: broken critical pages > SEO optimizations > nice-to-haves.
- Sample representative pages rather than auditing every page on large sites.
- Report both findings and actionable recommendations.

## Workflow

Word-for-word excerpt, not a result. Read the full SKILL.md ↓

Files of Site audit

sandbaseai/main1 file shown
SKILL.md
Show the full text54 lines

Site Audit

Comprehensive website auditing through SandBase. Crawl sites, analyze content, check SEO fundamentals, and assess structure. Read the API map before selecting a capability.

Call SandBase capabilities

Use the capability identifiers below as discovery hints, not MCP tool names. Find the matching endpoint with sandbase_discover(q: "<provider and capability>"); use its returned name in sandbase_inspect(name: "<returned name>"). Read inputSchema, pricing, and execute_as, then call sandbase_run using execute_as.arguments.name and schema-defined arguments. If a run_id is returned, poll sandbase_run_get(run_id: "<returned run_id>") within the task budget until completed or failed; report pending or failed runs without resubmitting them automatically.

Operating principles

  • Start with site structure before diving into page-level analysis.
  • Prioritize issues by impact: broken critical pages > SEO optimizations > nice-to-haves.
  • Sample representative pages rather than auditing every page on large sites.
  • Report both findings and actionable recommendations.

Workflow

1. Discover site structure

Use firecrawl_map to list all pages on the site. Use context_dev_crawl_sitemap for sitemap-based discovery.

2. Crawl and extract content

Use firecrawl_crawl for multi-page content extraction. Use context_dev_scrape_markdown for individual page content.

3. SEO analysis

Use dataforseo_v3_on_page_content_parsing_live for structured content analysis. Use dataforseo_v3_on_page_keyword_density_live for keyword optimization.

4. Visual and technical

Use context_dev_capture_screenshot for visual assessment. Use context_dev_scrape_html for technical HTML analysis.

Output

Return: site structure overview, page count, content assessment, SEO findings (title tags, headings, keyword usage), technical issues, and prioritized action items.

Example tasks

  • "Audit [website] — structure, content quality, and SEO health."
  • "How many pages does [website] have and what types of content?"
  • "Check the SEO basics for [URL] — title, headings, keyword density."
  • "Crawl [website] and identify thin or duplicate content pages."
  • "Take screenshots of [website]'s key pages for a visual audit."
1---
2name: site-audit
3description: Audit a website's content, structure, SEO health, and technical setup through SandBase. Use when asked for website audit, content audit, SEO health check, site structure analysis, or technical assessment.
4---
5 
6# Site Audit
7 
8Comprehensive website auditing through SandBase. Crawl sites, analyze content, check SEO fundamentals, and assess structure. Read [the API map](references/sandbase-api-map.md) before selecting a capability.
9 
10## Call SandBase capabilities
11 
12Use the capability identifiers below as discovery hints, not MCP tool names. Find the matching endpoint with `sandbase_discover(q: "<provider and capability>")`; use its returned `name` in `sandbase_inspect(name: "<returned name>")`. Read `inputSchema`, pricing, and `execute_as`, then call `sandbase_run` using `execute_as.arguments.name` and schema-defined `arguments`. If a `run_id` is returned, poll `sandbase_run_get(run_id: "<returned run_id>")` within the task budget until `completed` or `failed`; report pending or failed runs without resubmitting them automatically.
13 
14## Operating principles
15 
16- Start with site structure before diving into page-level analysis.
17- Prioritize issues by impact: broken critical pages > SEO optimizations > nice-to-haves.
18- Sample representative pages rather than auditing every page on large sites.
19- Report both findings and actionable recommendations.
20 
21## Workflow
22 
23### 1. Discover site structure
24 
25Use `firecrawl_map` to list all pages on the site.
26Use `context_dev_crawl_sitemap` for sitemap-based discovery.
27 
28### 2. Crawl and extract content
29 
30Use `firecrawl_crawl` for multi-page content extraction.
31Use `context_dev_scrape_markdown` for individual page content.
32 
33### 3. SEO analysis
34 
35Use `dataforseo_v3_on_page_content_parsing_live` for structured content analysis.
36Use `dataforseo_v3_on_page_keyword_density_live` for keyword optimization.
37 
38### 4. Visual and technical
39 
40Use `context_dev_capture_screenshot` for visual assessment.
41Use `context_dev_scrape_html` for technical HTML analysis.
42 
43## Output
44 
45Return: site structure overview, page count, content assessment, SEO findings (title tags, headings, keyword usage), technical issues, and prioritized action items.
46 
47## Example tasks
48 
49- "Audit [website] — structure, content quality, and SEO health."
50- "How many pages does [website] have and what types of content?"
51- "Check the SEO basics for [URL] — title, headings, keyword density."
52- "Crawl [website] and identify thin or duplicate content pages."
53- "Take screenshots of [website]'s key pages for a visual audit."
54 

Discussion

Alternatives

Agentic Browsing ReadinessAudit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).Marketing · MITBacklink Profile AnalysisBacklink profile analysis: referring domains, anchor text distribution, toxic link detection, competitor gap analysis. Works with free APIs (Moz, Bing Webmaster, Common Crawl) and DataForSEO extension. Use when user says backlinks, link profile, referring domains, anchor text, toxic links, link gap, link building, disavow, or backlink audit.Marketing · MIT/setup-cmsConnect a CMS to notfair SEO tools. Guides users through configuring WordPress, Strapi, Contentful, or Ghost — tests the connection, and writes credentials to .env.local. Once set up, seo-analysis automatically cross- references CMS content against Google Search Console data. Use whenever the user says "connect my CMS", "set up WordPress", "configure Strapi", "add Contentful", "connect Ghost", or "CMS setup". Also trigger if the user asks why no CMS data appears in a seo-analysis report. · MITBacklink checkBacklink profile for any domain — referring domains, authority, anchors, new/lost links, and a side-by-side vs a competitor. Use when asked "check my backlinks", "backlink profile of X", "who links to them", or "link gap vs competitor".Marketing · MIT