SkillsIndustries Page Structure: Agent Skill
Industries Page Structure: Agent Skill
Plan an industries hub and its industry page template: section order, launch industries and menu placement, benchmarked against category leaders.
Get full access to this skill and the tools to run it
For agents
Your AI gets this skill, your clients' context and the research tools, in Claude or any MCP client.
Connector URL: https://mcp.unilytics.ai/mcp
What you get
A Word document for the client's team or designer with wireframes, screenshots of other companies' public industries pages (the client's rivals and the best examples), the content each industry page needs, and checks for the build.
Deliverable: Word doc
When to use it
A page listing the industries a client serves, a template for each industry's page, or where industries sit in the site menu.
The steps
The skill takes your agent through these steps, in order. Each step's full instructions come with the skill when you run it through Unilytics.
- Inventory the client's site first
- Benchmark in two sets with one taxonomy
- Hand-author the sets
- Choose the launch set
- Pack the block models
- Capture proof
- Navigation and URLs
- Build the doc
- Verify
- Deliver
The full skill also covers: Before you start · Definition of done · Gotchas · Files · Rules for this skill.
Tools it needs, with or without Unilytics
Straight from the skill: the data each step needs and the tools that can supply it. Unilytics is one option, never a requirement.
| Capability | Ways to get it |
|---|---|
| Read benchmark and client pages as text (plain and rendered) | A fetch tool or Firecrawl scrape; or the Unilytics MCP content_scrape, js_scrape for rendered tabs and carousels, batch_scrape for a group of companies |
| Find moved pages, competitors and category leaders | A web search tool or a SERP API such as DataForSEO; or the Unilytics MCP web_research_tool or serp_results |
| Read the client's menu, sitemap and links | Fetch /sitemap.xml or a crawler such as Screaming Frog; or the Unilytics MCP site_map, link_extract or site_crawl |
| Demand for "<industry> <category>" terms | A keyword API such as DataForSEO or Keywords Everywhere; or the Unilytics MCP keyword_research |
| People Also Ask questions for the FAQ | A SERP API or AlsoAsked; or the Unilytics MCP serp_results or aeo_generate_prompts |
| Capture page sections to disk | A browser-automation extension such as Claude in Chrome, or Playwright; or the Unilytics MCP page_screenshot for a quick look |
| Code sets and print counts | data/benchmark.py (Python standard library) |
| Crop, draw the wireframes, build the .docx | Python with Pillow and python-docx (data/crop.py, data/wire_industries.py, data/build_industries_doc.py) |
| Gate the copy | data/qc_copy.py (Python standard library) |
| Render for the page check | LibreOffice (soffice) and poppler (pdftoppm), or Word |
| Validate the markup | Google's Rich Results Test |
Related skill in this collection: doc-template-design (building the doc in a client's template). Voice and banned
words, the site-wide menu and URL plan, and page titles, descriptions and markup are outside this skill: use the
client's own guidelines, or the tools you already use for them.
Without the Unilytics MCP
Every step runs without Unilytics. Without it, what you lose is one connection for several of the capabilities above: each one then comes from the other ways listed for it (a tool or account you already have, a vendor API, or a manual export). The Unilytics MCP is one optional way to get several of these tools in a single connection: https://unilytics.ai
New accounts start with 50 credits. Connecting, and reading your skills, projects and client context, costs nothing; research tools and some writes use credits.