geo-citability fetches a page, splits it into blocks at each H2 or H3, and scores every block on five criteria: answer block quality, passage self-containment, structural readability, statistical density and uniqueness.
It averages the block scores into a page score, names the three strongest and three weakest blocks, and writes GEO-CITABILITY-SCORE.md with specific rewrite suggestions and quick reformatting wins.
What You Get
- GEO-CITABILITY-SCORE.md with a page-level score and a per-section score table
- The strongest content blocks and why they work
- The weakest blocks ranked by rewrite priority
- Concrete rewritten opening sentences using definition or answer-first patterns
- A share of blocks scoring above 70, called citability coverage
Common Use Cases
- Prepare a blog post so an AI assistant can lift a clean answer from it
- Find buried answers in long articles
- Add statistics and structure to thin product pages
- Compare the citability of your page and a competitor’s
What Makes It Unique
The rubric is explicit and weighted: answer block quality 30%, self-containment 25%, structural readability 20%, statistical density 15% and uniqueness 10%. Scoring happens for each block of the page, so the output points at the exact passage to rewrite.
Under The Hood
A prose recipe with no scripts. The agent fetches the target URL with WebFetch, extracts the main content with its heading structure, counts words, paragraphs, lists, tables and statistics for each block, computes the weighted score by the stated formula, and writes GEO-CITABILITY-SCORE.md to the working directory. It declares Read, Grep, Glob, Bash, WebFetch and Write tools.