Skip to content
SkillModel-led3,460 tokens in use

geo-citability

Scores each content block of a web page from 0 to 100 on how likely AI systems are to quote it, and drafts rewrites for the weakest passages.

11,792 stars on the repository MIT Licensezubair-trabzada/geo-seo-claude · skills/geo-citability
curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/geo-seo-claude/main/install.sh | bash
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing geo-citability costs

61tokens idle
3,460tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldeclarednetworkdeclaredwrites filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity32
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers