Content Inventories

A content inventory catalogs what content actually exists, every page, document, and content object, and where it lives in the current structure. It's a necessary first step before any redesign, migration, or merger, because you can't restructure or improve what you haven't fully accounted for. Before starting, you need to decide the inventory's scope and granularity: whole pages, or the individual chunks and components pages are made of.

A typical inventory spreadsheet captures descriptive attributes, page ID, title, content type, topics, location, alongside governance attributes like author, owner, publication date, and status. For very large sites, doing the entire inventory in one pass can be impractical; a "rolling content inventory," working through one section at a time and cycling back around, is often more sustainable than trying to capture everything in a single exhausting effort.

A content inventory is tedious in exactly the way that pays off later, every hour spent cataloging now is an hour someone doesn't have to spend guessing what exists once the redesign is underway.

Exercise

The scenario: A digital agency is preparing to migrate a regional newspaper's website to a new CMS. The site has run for twelve years and accumulated thousands of articles, several hundred static pages, multiple embedded media types, and an unknown number of broken links. The project timeline is eight weeks, with a small team available.

Given the eight-week timeline and twelve years of accumulated content, which approach to conducting this inventory is most realistic?
Try It With Your Data: Duplicate Detection

Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.

What this prompt is made of (RICE breakdown)
R

Role

Casts the AI as: You're a content analyst specializing in identifying redundant and duplicate content.

I

Instructions

Names 4 specific outputs to produce, so the response comes back structured rather than a general summary.

C

Context

Content domain, Known history and User impact tell the AI what your specific situation is, not a generic one.

E

Expected format

Grouped findings by severity with specific merge recommendations

Paste titles and short descriptions, one per line
e.g. "API reference docs"
Migrations, reorgs, or multiple authors that could explain overlap
How duplicate content affects users
Assembled prompt

        
        
      
Try It With Your Data: Age and Staleness Analyzer

Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.

What this prompt does

Identify outdated content based on update dates, product version history, and staleness signals. Prioritize content refresh based on user impact and staleness severity.

  • Regular content maintenance cycles
  • After product releases or major updates
  • When support tickets indicate outdated documentation
  • As part of comprehensive content audits
One row per page: Title | URL | Last Updated | Category
One release per line, e.g. "v3.0 (2024-09-01): Major auth overhaul"
Assembled prompt

        
        
      
Try It With Your Data: Quality Pattern Analysis

Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.

What this prompt does

Use this prompt when: During content audit to find redundancy.

  • After completing content inventory with quality signals
  • When quality problems seem widespread but unclear where to focus
  • To distinguish systemic issues from one-off problems
  • Before allocating resources for content improvement
Paste rows including: title/URL, last updated, word count, content type, category, author, traffic, ratings, whatever you have
Paste the criteria you're scoring against, or leave the defaults below
Whole number
e.g. "2019 to 2026"
From support tickets or research
Assembled prompt