Skip to content
SkillModel-led2,842 tokens in use

geo-proposal

Turns a saved GEO audit into a client-ready proposal with findings, three priced service packages, an ROI projection, a timeline and terms.

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

83tokens idle
2,842tokens 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
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output7/15
  • 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-proposal loads a prospect’s saved GEO audit, pulls out the overall score, the top three critical findings and the quick wins, and fills a proposal template with them. It recommends a Basic, Standard or Premium package from the score and states the findings in business terms.

The proposal is saved as markdown under a proposals folder in the home directory, and the prospect record is updated to the proposal stage.

What You Get

  • A proposal markdown file named by domain and date
  • A package recommendation based on the audit score
  • Three service tiers with included work, expected score gains and contract length
  • An ROI projection table for four scenarios
  • An updated prospect record with the proposal file path

Common Use Cases

  • Send a proposal the same day an audit is finished
  • Override the package, client name or monthly price with command options
  • Generate a proposal from an audit file by path
  • Move a prospect from qualified to proposal in the pipeline

What Makes It Unique

It ties the pitch to audit data: the score picks the tier (0-40 Premium, 41-60 Standard, 61-75 Basic) and each critical finding becomes a pain point with what was found, the business impact, the fix and the timeline. The template carries prices in euros, which you edit to suit your own agency.

Under The Hood

A prose recipe with no scripts. The agent reads audit files from ~/.geo-prospects/audits, may use WebFetch, fills the template, writes the proposal into ~/.geo-prospects/proposals and edits ~/.geo-prospects/prospects.json in the home directory. It declares Read, Write, Bash, Glob and WebFetch tools. The price figures, projected gains and market statistics in the template are written into the skill and are not computed from data, so review them before sending.

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