Borrowing it
Nothing to install: this file belongs to prashishh/seo-geo-report-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/prashishh/seo-geo-report-engine/main/.agents/skills/proposal-builder/SKILL.mdgit clone --depth 1 https://github.com/prashishh/seo-geo-report-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/prashishh/seo-geo-report-engine/proposal-builder)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/proposal-builder"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/proposal-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/proposal-builder"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/proposal-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.01551 |
| Opus 5 | $0.00054 | $0.00776 |
| Sonnet 5 | $0.00022 | $0.00310 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
proposal-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
proposal-builder
Turns a client's profile + research into a branded growth-proposal PDF that looks like the
reference decks. You compose the content (a proposal.yml); the renderer handles layout, brand,
charts, and PDF. Depth methodology lives in playbooks/proposal-methodology.md.
Inputs
projects/<client>/client.yml— profile, competitors, target keywords, brand, locale.- Any research already in
projects/<client>/research/(keyword, competitor, GEO, audit outputs). - The brief / notes in
projects/<client>/inputs/.
If the project doesn't exist yet, run /new-client first (or create the folder + client.yml
from templates/client.yml.example).
Workflow
-
Resolve context.
./bin/mkt config show --project <client>. Readclient.yml, the brief, and existing research. Identify vertical, ICP, market/locale, competitors, budget, time horizon. -
Fill research gaps (Ahrefs MCP first — see
knowledge/ahrefs-mcp-map.md). Only pull what the proposal needs; don't boil the ocean.- Opportunity sizing:
keywords-explorer-*for category volume; market/TAM from the brief. - Competitive landscape:
site-explorer-organic-competitors,-top-pages,-domain-rating. - GEO angle:
brand-radar-sov-overview/-mentions-overviewfor AI share-of-voice (use thegeo-auditskill if a full GEO read is wanted). - Save anything reusable into
research/as you go.
For first-strategy or client-hook proposals, these are mandatory unless explicitly out of scope: location/market context, keyword demand, domain authority/DR, named competitors, SEO current state, GEO/AI current state, and at least two charts/visual punchlines. If a provider call fails, include a dated "not captured" row plus the rerun path rather than dropping the section.
- Opportunity sizing:
-
Choose the spine. Default to the proven structure (adapt to the client):
- Executive summary + 3 pillars (Foundation → Wide Net/Acquisition → Conversion/Lifecycle)
- Current-state scorecards (location, authority, keyword demand, SEO/GEO readiness)
- The opportunity (market size, where the headroom is)
- Competitor and keyword gap charts
- Audience / ICP (segments, where they are)
- Pillar deep-dives with deliverables
- Roadmap (workstream gantt)
- Scenario projection (conservative / probable / aggressive) + metrics table
- KPI scorecards + a clear next step (CTA)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 107 lines · 108 tokens per session scan A b3f8e70ed80b
proposal-builder is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 1,551 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
visibly-seo-pdf-build
Build a clean, brand-compliant PDF from an analysis or offer. Use when the user asks to generate, render, or export a client-ready PDF presentation or document with their corporate identity — cover page, header/footer, section bars, tables, ROI boxes.
citedy-lead-magnets
Generate AI-powered lead magnets — checklists, swipe files, and frameworks that convert visitors into subscribers. PDF generation with optional AI illustrations. No competitors in any MCP/skill store. Powered by Citedy.
market-report-pdf
Generate a professional, visually polished PDF marketing report using the Python script scripts/generatepdfreport.py. This skill collects all available audit and analysis data, structures it into the expected JSON format, invokes the script, and produces a branded PDF with score gauges, bar charts, comparison tables…
geo-proposal
Auto-generate a professional, client-ready GEO service proposal from audit data. Creates a full proposal in markdown and PDF including executive summary, findings, recommended service packages (Basic/Standard/Premium), pricing, timeline, and terms. Use when user says "proposal", "proposta", "offerta", "preventivo"…
geo-report-pdf
Generate a professional PDF report from a GEO audit using pandoc + Chrome headless. Converts GEO-AUDIT-REPORT.md into a styled, client-ready PDF with a cover page, color-coded score tables, severity-tagged findings, and a 90-day roadmap.
content-amplifier
Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…