What does this skill do, and when should you use it?
geo-proposal is one of 16 skills bundled in the geo-seo-claude repository, focused on the sales step of a GEO agency workflow. It reads audit data previously produced for a domain (via /geo audit or /geo quick), translates technical gaps into business pain points, and renders a complete markdown proposal. The document includes an executive summary, audit findings, three priced service tiers (Basic €2,500/mo, Standard €5,000/mo, Premium €9,500/mo), ROI projections, a six-month engagement timeline, and terms. It recommends a tier automatically based on the prospect's GEO score and logs the proposal in a local CRM directory. It is a sales enablement tool, not an audit tool — it requires existing audit output to function.
1) Looks for an audit file in ~/.geo-prospects/audits/ for the given domain and suggests running /geo quick if none exists; 2) extracts the overall and per-category GEO score, top three critical findings, quick wins, business type, and estimated traffic impact; 3) recommends a service tier from the score (0-40 → Premium, 41-60 → Standard, 61-75 → Basic); 4) fills a full proposal template — executive summary, AI-search market stats, findings with business impact, three-tier pricing table, ROI scenario table, and a 30-day validity window; 5) saves the proposal to ~/.geo-prospects/proposals/<domain>-proposal-<date>.md and updates the prospect's status to 'proposal' in ~/.geo-prospects/prospects..
- A GEO/SEO agency that just finished a client audit and needs a polished, sendable proposal in minutes
- A freelance consultant pitching AI-search optimization to a prospect who wants a professional document to accompany the call
- A sales team standardizing proposal format across prospects, with benchmark comparisons and tiered pricing built in
- Teams using the repo's geo-prospect CRM flow who want audits to automatically advance to the proposal stage with an audit trail
How do you install this skill?
- The template embeds unsourced market statistics (527% YoY growth, 4.4x conversion, Gartner -50%) as facts in client-facing proposals; verify or remove them before use to avoid misleading clients.
- ROI projections use hardcoded, unevidenced score-improvement and traffic-growth ranges and should not be presented to clients as-is.
- The skill silently mutates ~/.geo-prospects/prospects. and generates files with no confirmation or rollback; the data directory is not removed on uninstall and must be cleaned manually.
- Pricing, contract terms and T&Cs are preset template text; seek legal review before real commercial use.
- No Chinese support; EUR pricing is hardcoded and non-euro users must rewrite it.
- This is a static review without execution; the skill's key paths have no test coverage.
- Shell / CLI
- Network access
- Local filesystem
Claude Code CLI (for /geo command routing)geo-seo-claude skill collection (audit data from /geo quick or /geo audit)
The skill installs as part of the geo-seo-claude repo; there is no standalone install:
- One-command (macOS/Linux): curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/geo-seo-claude/main/install.sh | bash
- Windows: run the install-win.sh one-liner from Git Bash
- Requirements: Python 3.8+, Claude Code CLI, Git. Skills land in ~/.claude/skills/ with Python deps in an isolated venv at ~/.claude/skills/geo/.venv/. Uninstall with ./uninstall.sh; note the ~/.geo-prospects/ data directory is not removed automatically.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/zubair-trabzada/geo-seo-claude.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/geo-proposal" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
In Claude Code, run an audit first (e.g. /geo quick electron-srl.com), then:
/geo proposal electron-srl.com
Or with tier and client name:
/geo proposal electron-srl.com --tier standard --client-name "Electron Srl"
Or point directly at an audit file:
/geo proposal ~/.geo-prospects/audits/electron-srl.com-2026-03-12.md
Trigger phrases include "proposal", "proposta", "offerta", "preventivo", and "generate proposal". Output is markdown; the console suggests /geo report-pdf for a visual PDF version (that capability belongs to the sibling geo-report-pdf skill). Optional --monthly EUR overrides pricing; agency name, calendar link, and similar placeholders must be filled in manually.
What are this skill's strengths and limitations?
- Proposal content is driven by real audit data — scores, findings, and tier recommendations are auto-filled, not generic boilerplate
- Complete out-of-the-box sales package: three pricing tiers, ROI scenario table, and a six-month delivery timeline
- Integrates with the geo-prospect CRM skill — saves the file and advances the pipeline status automatically
- MIT-licensed and free; markdown output is easy to rebrand and edit
- Depends on the repo's audit skills producing data first; it cannot generate a proposal from scratch
- ROI projections and headline market stats (e.g. +527% AI traffic growth, 4.4x conversion) are hardcoded template assumptions without cited sources — verify before showing clients
- Default pricing is in euros and tier structure may not match your own service catalog; manual adjustment required
- No automated tests in the SKILL.md, and PDF output is a sibling skill's job, not this skill's
- Sales copy such as 'Why Us' and agency identity are placeholders that must be rewritten to avoid presenting false claims to clients
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| GEO Proposal Generator this page | 44 · Not recommended | ★ 11k | 20d ago | MIT |
| GEO Monthly Delta Report Generator | 46 · Use with care | ★ 11k | 20d ago | MIT |
| GEO PDF Report Generator | 50 · Use with care | ★ 11k | 20d ago | MIT |
| huashu-md-html Publishing Pipeline | 57 · Use with care | ★ 915 | 12d ago | MIT |
| Obsidian Markdown Editor | 57 · Use with care | ★ 50k | 1mo ago | MIT |
How did FollowSkills review this skill?
Declared allowed-tools include Read/Write/Bash/WebFetch; the skill writes to ~/.geo-prospects/proposals and mutates prospects. (setting status to 'proposal') without explicit user confirmation, rollback guidance, or data-flow disclosure. The template injects unsourced marketing statistics (+527%, 4.4x, -50% Gartner claim) directly into client-facing commercial documents, creating a risk of misleading third parties. No sensitive-data handling guidance; deducted to a mid score.
The workflow is self-consistent with a clear path (load audit → fill template → write file → update record) and clear confirmation output. However, missing-audit handling is only a suggestion to run /geo quick first; there is no error handling or diagnosable feedback for corrupt prospects., abnormal parameters, or WebFetch failure. It depends on upstream skill output; static review cannot verify key paths, capped below 10, deducted to 9.
Trigger words are explicit (proposal/proposta/offerta/preventivo) and the scenario (agency proposals to clients) with tiered pricing logic is clear. But non-fit boundaries are undeclared (no audit data, non-EUR markets), the template hardcodes EUR and European client examples, and there is no Chinese-language support, limiting fit for Chinese users; deducted to 7.
Frontmatter includes version, tags and allowed-tools; documentation is well layered (command → workflow → template → pricing logic) and MIT licensed. However, there is no changelog, no known-limitations disclosure, unclear maintenance ownership and update path, and the description promotes a paid skool community, deducting to 9.
The template is structurally complete (executive summary, findings, packages, ROI, timeline, terms) and can directly produce a markdown proposal, offering marginal value over manual drafting. But many placeholders require real audit data, and score-improvement deltas and ROI growth rates are hardcoded invented figures; output needs human fact-checking before client delivery. Static cap 7, deducted to 6.
Industry statistics (527% YoY, 4.4x conversion, Gartner -50%) carry no citations and are shared with the README's same unsourced dataset. The repository contains tests for fetch_page.py SSR heuristics, but these do not cover this skill's proposal-generation path. No reproducible evidence exists for this skill; deducted to 3.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →