Crawl a website's sitemap and blog index to build a complete content inventory. Lists every page with URL, title, publish date, content type, and topic cluster. Groups content by category and topic. Optionally deep-reads top N pages for quality analysis and funnel stage tagging. Use before SEO audits, content gap analysis, or brand voice extraction.
SkillScore73Maintained
Automatic
◆Marketing & Content pack
Last verified 8/16/2026
What it changes
Passed 14 of 19 test cases with the skill, and 8 of 19 without it.
Without skill41%
With skill73%
Checks it passed that the model alone missed
Attempts fetching sitemap.xml first
Includes by_type in the summary object
Includes by_topic in the summary object
and 6 more in the full report
7 fixed9 passed either way6 still failing0 broke
Pass-rate lift
+32 pp
Tokens
+89%
Agent turns
0%
Response time
-52%
Model gemini-3.6-flashMeasured 8/16/2026v116 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
When detailed page evaluation is enabled, what boolean field names inside the deep_analysis object report visual asset and call-to-action presence?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses has_images as a boolean field name
Missed
Passed
Uses has_cta as a boolean field name
Passed
Passed
case-18 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md192 lines2 filesincludes scripts
Site Content Catalog
Crawl a website's sitemap and blog to build a complete content inventory — every page cataloged with URL, title, date, content type, and topic cluster. Groups content by category, identifies publishing patterns, and optionally deep-analyzes top pages.
Quick Start
# Basic content inventory
python3 scripts/catalog_content.py --domain "example.com"
# With deep analysis of top 20 pages
python3 scripts/catalog_content.py --domain "example.com" --deep-analyze 20
# Output to specific file
python3 scripts/catalog_content.py --domain "example.com" --output content-inventory.json
Inputs
Parameter
Required
Default
Description
domain
Yes
—
Domain to catalog (e.g., "example.com")
deep-analyze
No
0
Number of top pages to deep-read for content analysis
output
No
stdout
Path to save JSON output
include-non-blog
No
true
Also catalog landing pages, docs, etc. (not just blog)
Cost
Sitemap/RSS crawling: Free (direct HTTP requests)
Apify sitemap extractor (fallback): ~$0.50 per site
Deep analysis: Free (WebFetch on individual pages)
Process
Phase 1: Discover All Pages
The script attempts multiple methods to find all pages on a site, in order:
Discover newsletters in a target niche relevant to your ICP, evaluate audience fit, estimate reach and CPM, and output a ranked shortlist of sponsorship opportunities. Uses web search to find newsletters, then scores each against ICP alignment criteria. Use when a marketing team wants to reach an existing engaged audience for less than the cost of building their own, or when testing a new channel before committing.