Website Health Auditor

Site audit

by sandbaseai · Apache-2.0 license · ★ 203 on GitHub

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.

---
name: site-audit
description: 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.
---

# Site Audit

Comprehensive 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.

## 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.

Overview

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

Manual install (npx, ZIP)

Claude Codenpx skills add sandbaseai/sandbase-skills --skill site-audit -g -a claude-code

Claude Code (degit)npx degit sandbaseai/sandbase-skills/research/site-audit#main ~/.claude/skills/site-audit

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md2.5 KB

Read SKILL.md here

sandbaseai/main1 file shown

SKILL.md2.5 KB

Browse every file on GitHub↗

SKILL.md

Show the full text54 lines

site-audit/SKILL.md54 lines · 2.5 KB

PreviewCode

Outline

RawView on GitHub

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	---
2	name: site-audit
3	description: 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
8	Comprehensive 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
12	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.
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
25	Use `firecrawl_map` to list all pages on the site.
26	Use `context_dev_crawl_sitemap` for sitemap-based discovery.
27
28	### 2. Crawl and extract content
29
30	Use `firecrawl_crawl` for multi-page content extraction.
31	Use `context_dev_scrape_markdown` for individual page content.
32
33	### 3. SEO analysis
34
35	Use `dataforseo_v3_on_page_content_parsing_live` for structured content analysis.
36	Use `dataforseo_v3_on_page_keyword_density_live` for keyword optimization.
37
38	### 4. Visual and technical
39
40	Use `context_dev_capture_screenshot` for visual assessment.
41	Use `context_dev_scrape_html` for technical HTML analysis.
42
43	## Output
44
45	Return: 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