Proposal Generator logo

Proposal Generator

Organization
Amazon-Quick
proposal-generator

Creates professional, customized sales proposals and quotes for small business deals. Auto-brands with the sender's identity from session context or memory. Use when user says 'write a proposal', 'create a quote', 'draft a bid', 'put together a proposal for [client]', 'help me price this deal', 'generate an SOW', 'send a proposal', 'write a quote', 'respond to this RFP', 'draft a statement of work', or 'proposal for [project type]'.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill nameproposal-generator
Stars
50
Forks
4
Bundled files
1
LicenseMIT-0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Proposal Generator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/sales/proposal-generator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/sales/proposal-generator .claude/skills/proposal-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Proposal Generator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Proposal Generator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Proposal Generator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Overview

Creates professional sales proposals tailored to each specific prospect. Auto-brands with the sender's real identity. Supports Quick Quotes (under $5K), Standard Proposals ($5-50K), and Enterprise Proposals ($50K+). Outputs as DOCX documents ready to send.

Workflow

<Definition - Seller Identity Resolution> Resolve in priority order (stop at first match):

  1. Explicit inputs: If seller_name or seller_company were passed, use them
  2. Memory: Check long-term memory for previously saved seller identity
  3. Session user_identity: Read injected user_identity block (name, email, infer company from domain)
  4. Ask user: If all above fail, ask once and save to memory for future runs

First-run confirmation: "I'll prepare this proposal from [seller_name] at [seller_company] - sound right?" On subsequent runs: skip confirmation entirely. </Definition - Seller Identity Resolution>

<Definition - Proposal Tiers>

TierDeal SizePagesSections
Quick QuoteUnder $5K1-2Problem, Solution, Pricing, Next Steps
Standard$5K-$50K3-5Executive Summary, Understanding Your Needs, Our Approach, Deliverables, Timeline, Investment, Why Us, Next Steps
Enterprise$50K+6-10Cover, Executive Summary, Situation Analysis, Proposed Solution, Implementation Plan, Team and Resources, Investment Options, Risk Mitigation, Case Studies, Terms, Next Steps
</Definition - Proposal Tiers>

<Definition - Self-Check> Before generating DOCX, verify:

  • Executive summary is standalone-readable (a stranger could understand the deal)
  • Every deliverable maps to a stated need from the prospect
  • Pricing is unambiguous (no ranges unless intentional)
  • Seller identity fields are populated (not placeholder names)
  • Timeline uses specific dates

If any check fails, fix it before generating the document. </Definition - Self-Check>

<Definition - Skill-Ready Outputs> Two formatted blocks always included:

  1. Proposal Sent table (for deal-pipeline-manager): Prospect, Amount, Date Sent, Follow-Up Due
  2. Pending Decision table (for follow-up-cadence): Contact, Company, Proposal Date, Recommended Follow-Up Day </Definition - Skill-Ready Outputs>

<Workflow - Generate Proposal description="Create a professional proposal document from deal context." tools=[web_search, url_fetch, recall_memories, file_rag_search, fdfind, file_read, file_read_docx, file_write, file_edit, run_javascript, open_in_session_tab] triggers=["write a proposal", "create a quote", "draft a bid", "put together a proposal for", "generate an SOW", "send a proposal", "respond to this RFP", "draft a statement of work"]

  1. [Agent] Resolve seller identity per <Definition - Seller Identity Resolution>. Check explicit inputs, then memory, then session user_identity. Validate: seller_name, seller_company, and seller_email are all populated with real values (not placeholders). If fails: Ask user once: "What name and company should appear on this proposal?" Save answer to memory.

  2. [Agent] Gather deal context. Search connected local folders for files matching prospect_company name (file_rag_search, fdfind). If deal notes found, read and extract context. Research prospect via web_search/url_fetch for company news and positioning context. Validate: Have at minimum: company name, scope of work, and pricing. If fails: Ask "What did you discuss with them, what will you deliver, and what will you charge?"

  3. [Decide] Select proposal tier per <Definition - Proposal Tiers> based on deal size.

    • Under $5K: Quick Quote
    • $5K-$50K: Standard Proposal
    • $50K+: Enterprise Proposal Validate: Tier matches deal size and buyer expectations. If fails: Default to Standard Proposal.
  4. [Agent] Write complete proposal copy section by section per the selected tier structure. Apply writing principles: lead with their goals, quantify outcomes, present 2-3 pricing options, include "What's NOT included", make next steps one action. Write executive summary last, place it first. Validate: Run <Definition - Self-Check>. All items pass. If fails: Fix failing items. Ask user for clarification on unclear scope or pricing if needed.

  5. [Agent] Generate DOCX document via run_javascript (docx library). Apply formatting: cover page with seller identity, professional typography, bold key numbers, table format for pricing, footer with seller company and page numbers. Validate: Document generates successfully. Seller identity is correct throughout. All sections present. If fails: Deliver as well-formatted markdown in chat.

  6. [Ask user] Open document in session tab for review. Present cover email text alongside. Ask: "Ready to send, or want changes?" Validate: User approves or requests edits. If fails: Apply edits and re-present.

  7. [Agent] Deliver per user direction. If email tools are available and user approves sending: attach DOCX and send with cover email. Otherwise: save locally and confirm path. Produce skill-ready outputs per <Definition - Skill-Ready Outputs>. Validate: Proposal delivered. Skill-ready outputs present. If fails: Save document and provide manual sending instructions.

</Workflow - Generate Proposal>

<Template - Cover Email> Subject: [Project Name] Proposal - [Prospect Company]

Hi [First Name],

Following our conversation about [specific topic], I've put together a proposal outlining how we can [key outcome].

Happy to walk through it together - would [Day] at [Time] work for a quick 15-min review?

[seller_name] [seller_company] [seller_email] </Template - Cover Email>

<Template - Quick Quote Structure>

[Project Name] - Quote

Prepared for: [Prospect Company] Prepared by: [seller_name] | [seller_company] Date: [Today's date]

The Challenge

[1-2 sentences about their stated need]

Our Solution

[What we'll deliver, in bullet points]

Investment

OptionWhat's IncludedPrice

What's NOT Included

[Explicit exclusions]

Next Steps

[One action for the buyer] </Template - Quick Quote Structure>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Proposal Generator AI skill do?

Creates professional, customized sales proposals and quotes for small business deals. Auto-brands with the sender's identity from session context or memory. Use when user says 'write a proposal', 'create a quote', 'draft a bid', 'put together a proposal for [client]', 'help me price this deal', 'generate an SOW', 'send a proposal', 'write a quote', 'respond to this RFP', 'draft a statement of work', or 'proposal for [project type]'.

Why use Proposal Generator on TypingMind?

Because you install it once and use it with any model. Proposal Generator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Proposal Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/sales/proposal-generator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Proposal Generator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Proposal Generator?

As many as you like. As long as a model supports skills, you can use Proposal Generator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Proposal Generator AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇