Takes a raw keyword export CSV with search volumes plus your current site structure and turns it into page-ready clusters instead of a flat keyword list. It groups semantically related terms, maps each cluster to an existing page or flags where a new page is needed, and scores opportunity by combined volume, competition, and business relevance. The output also flags cannibalization risk between overlapping clusters and ranks the top five clusters worth pursuing first.
Roots a keyword or content strategy in Clayton Christensen's Jobs-To-Be-Done framework instead of raw search volume, starting from a single seed topic.
- Input: just a seed topic
- Identifies the functional, emotional, and social jobs customers are trying to accomplish
- Translates each job into 3-5 real search queries, problem-focused versus solution-focused
- Maps every query to a funnel stage: awareness, consideration, decision, retention
- Output: a JTBD query map table plus a job prioritization matrix and content gap analysis
Branches a single seed keyword out into a list of long-tail queries a real customer might type, ranked by commercial intent rather than just volume.
- Inputs: seed keyword, how many long-tail keywords to generate, and a description of the product or service
- Returns the full list of long-tail variations
- Follows up by picking the three with the strongest commercial intent and explaining why
- Meant to run once per seed keyword from a broader seed list
- Feed the winning keywords straight into the keyword clustering prompt next
For a blog post that already has its primary keyword in place, this suggests a set number of LSI, or Latent Semantic Indexing, related terms to deepen topical coverage.
A follow-up pass maps each suggested LSI keyword to the specific section or paragraph where it fits naturally, so you're not just left with a word list. The prompt itself warns against forcing every term in, since over-applying LSI keywords leads to stuffing.
Starting point for keyword research before you have any other data —
specify a main category, how many topics you want, and how many table
columns to spread them across, and it returns a table of semantically
distinct seed keywords under that niche. The example in the prompt uses
'gym exercise' with 30 topics across 5 columns as a working default if
you're unsure what numbers to pick.