Skip to content
SkillModel-led1,706 tokens in use

geo-prospect

A small CRM inside Claude Code for GEO agencies: track prospects from lead to won in a local JSON file, run quick audits and see pipeline revenue.

11,792 stars on the repository MIT Licensezubair-trabzada/geo-seo-claude · skills/geo-prospect
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-prospect costs

87tokens idle
1,706tokens 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

shelldeclared and detectedwrites filesdeclared and detected

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 →
Good
  • Frontmatter12/15
  • Structure25/25
  • Examples12/15
  • Output5/15
  • 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-prospect manages the sales side of a GEO agency. Each prospect is a record in ~/.geo-prospects/prospects.json with an ID, company, domain, contact, status, GEO score, audit and proposal file paths, deal value and dated notes.

Commands create prospects, list and filter them by stage, show one in full, run a quick GEO audit and save it, add notes, change status, mark a deal won or lost and print a pipeline summary with committed monthly revenue.

What You Get

  • A prospects.json database created in the home directory on first use
  • Commands for new, list, show, audit, note, status, won, lost and pipeline
  • A table view of prospects with status, score and value
  • A pipeline summary with committed monthly revenue, pipeline value and next actions
  • Audit snapshots saved per domain and date

Common Use Cases

  • Log a new lead and score it with a quick audit
  • Record why a deal was lost for later reference
  • See how much monthly revenue is committed and how much is in the pipeline
  • Find which prospects need a proposal or a follow-up

What Makes It Unique

It is a CRM that lives in a single JSON file with no outside service, and it is wired to the rest of the toolkit: a quick audit stores its score on the prospect, and a score under 55 triggers a suggestion to generate a proposal.

Under The Hood

A prose recipe with no scripts. The agent reads and rewrites ~/.geo-prospects/prospects.json in the home directory, creates the audits and proposals folders there with mkdir, and saves audit output as markdown files under that folder. The quick audit command calls the main geo skill, which fetches the prospect’s website. It declares Read, Write, Bash and Glob tools. Nothing is sent to an outside service, and the data stays on the machine.

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