pf-proposal-generator

Generate polished, branded client proposals from discovery notes in 20–40 minutes instead of 3–5 hours. No subscription, no per-user fee, data stays local.

An alternative to proposal software like Proposify ($588–$7,800/yr) and PandaDoc ($360–$2,160/yr). Transform discovery call notes, emails, and client requirements into persuasive, professionally formatted proposals without proprietary templates or expensive SaaS.

Installation

Download the pf-proposal-generator.plugin file
Open Claude Desktop and navigate to Settings > Plugins
Click Install Plugin and select the downloaded .plugin file
The plugin will be installed and available immediately

Note: All data stays local on your machine. No external API calls or cloud storage required.

Why This Plugin

Consultants, agencies, and freelancers spend 3–5 hours per proposal: gathering requirements, outlining sections, writing value propositions, pricing, and formatting. Most use Word templates (slow, repetitive) or subscribe to $50–$650/month proposal software (expensive, inflexible). This plugin gives you the same proposal generation as SaaS platforms, running entirely within Claude.

Transform discovery notes into a complete proposal with an executive summary, client-specific value proposition, scope of work, timeline, pricing breakdown, and legal terms — all formatted professionally and ready to send.

Quick Start

/proposal-setup
/proposal-intake
/proposal-structure
/proposal-draft
/proposal-pricing
/proposal-review

Or run the full pipeline in one command:

/proposal-pipeline

Commands

Command	Stage	What It Does
`/proposal-setup`	0 — Setup	Initializes workspace, checks Python dependencies, generates config file with business name
`/proposal-intake`	1 — Intake	Captures client info from discovery notes (emails, meeting notes, chat) into a structured intake record
`/proposal-structure`	2 — Structure	Recommends proposal outline and section order based on proposal type and client pain points
`/proposal-draft`	3 — Draft	Writes full proposal content for all sections (executive summary, approach, scope, timeline, terms)
`/proposal-pricing`	4 — Pricing	Builds pricing table with line items, taxes, discounts, and payment schedule using Python arithmetic
`/proposal-review`	5 — Review	Evaluates proposal across 6 quality dimensions, saves scorecard, generates final DOCX ready to send
`/proposal-pipeline`	Full Pipeline	Runs all stages sequentially (intake → structure → draft → pricing → review)
`/proposal-status`	—	Shows current proposal status, which skills have run, and what's pending

How It Works

Each command follows a three-step pattern:

Step 1 — Gather: Claude collects input from uploaded files (discovery notes, emails), pasted text, or conversational input. Accepts unstructured notes, meeting transcripts, or detailed requirements.

Step 2 — Interpret: Claude's AI layer extracts client information, pain points, services requested, and budget hints from raw notes. Recommends proposal structure based on client industry and proposal type. Writes persuasive, client-specific sections (not generic templates). Calculates pricing using Python (verify all figures before sending).

Step 3 — Generate: Claude scores the proposal across 6 quality dimensions (clarity, completeness, pricing coherence, tone, value proposition, legal compliance) and produces a final DOCX document with professional formatting, page breaks, and table of contents.

AI-Powered Features

Discovery Note Parsing: Extracts client name, contact, industry, services requested, pain points, budget hints, and timeline from unstructured meeting notes, emails, or voice transcripts
Client-Specific Proposals: References client name, pain points, and industry throughout the proposal (not generic boilerplate)
Proposal Structure Recommendation: Recommends optimal section order based on proposal type (design, development, consulting, marketing, strategy, coaching) with rationale
Value Proposition Synthesis: Generates compelling executive summary that opens with the client's primary pain point and closes with specific business outcomes
Scope Specificity: Converts vague service descriptions ("design work") into specific deliverables (e.g., "Brand guidelines document", "5 homepage wireframes")
Pricing Accuracy: Uses Python Decimal arithmetic (no rounding errors) to calculate line totals, subtotals, discounts, taxes, and payment schedules
Quality Scorecard: Evaluates proposal across clarity, completeness, pricing coherence, tone, value proposition strength, and legal compliance; provides specific improvement suggestions
Industry Calibration: Adjusts tone and terminology based on client's industry (SaaS vs. healthcare vs. nonprofit)

Comparison vs. Proposify and PandaDoc

Feature	pf-proposal-generator	Proposify	PandaDoc
Proposal generation	✅	✅	✅
Client intake capture	✅	✅	✅
Proposal templates	✅ (customizable)	✅ (100+ pre-built)	✅ (600+ pre-built)
E-signature	❌	✅	✅
Client portal/tracking	❌	✅	✅
Proposal analytics (open/read time)	❌	✅	✅
Payment integration	❌	✅	✅
AI content generation	✅ (native)	✅ (GPT integration)	✅ (AI writing assistant)
CRM integration	❌	✅	✅
Team collaboration	❌ (single-user)	✅	✅
Pricing calculator	✅ (Python-driven)	✅	✅
Quality review workflow	✅ (6-dimension scorecard)	❌	❌
Annual cost	Included	$588–$7,800/yr	$360–$2,160/yr

Best for: Freelancers, small consulting firms (5–20 people), agencies building custom proposals, anyone who values proposal customization over templates, teams wanting to avoid subscription costs, organizations needing full data control.

Note: This plugin generates proposals only. It does NOT include e-signatures, client portal, payment processing, or analytics. If you need those features, Proposify/PandaDoc are more comprehensive.

Context & Performance Guide

File Layout

$WORKSPACE/
├── inbound/           # Upload discovery notes, client emails, requirements
│   └── *.txt, *.md, *.docx, *.pdf
├── processing/        # Intermediate JSON files (intake, structure, draft, pricing, review)
│   ├── proposal-intake.json
│   ├── proposal-structure.json
│   ├── proposal-draft.json
│   ├── proposal-pricing.json
│   ├── proposal-review.json
│   └── *.py           # Python generation scripts
├── outbound/          # Final DOCX documents
│   └── proposal-{client_name}-{date}.docx
├── archive/           # Prior versions (timestamped)
└── .proposal/
    ├── config.json    # Business name, currency, proposal author
    ├── logs/
    └── templates/     # Base proposal templates (auto-installed)

Discovery Note Best Practices

For optimal proposal generation, structure your discovery notes like this:

What to include:

Client name and company
Client's pain points (stated in their words or your interpretation)
Services they requested (feature list, functionality, scope)
Budget hints (if mentioned: "around 10K", "$150/hr", "we have $20K")
Timeline/deadline (if mentioned: "launch by Q2", "3-month project")
Industry context (e.g., "SaaS", "nonprofit", "healthcare")
Who are the competitors (if relevant)
Why they're reaching out (urgent need? planned project? RFP response?)

What to avoid:

Long rambling paragraphs (bullet points work better)
Generic details ("they need a website" — too vague)
Incomplete info (capture first impression, follow up later)

Example good note:

Client: Acme Corp (B2B SaaS, 25 people)
Contact: Jane Smith, Head of Operations
Pain: Manual workflow approval takes 3–5 days per request; slowing sales

Services requested:
- Design new workflow UI
- Implement user authentication
- Build approval dashboard
- Train team on new system

Budget: ~$25K (no hard limit)
Timeline: Launch by June 2026 (4 months)

Estimated Cost per Use

Disclaimer: Token estimates are approximate and based on typical usage patterns measured from skill prompt sizes. Actual costs vary with input data size, conversation length, and complexity. Estimates use Claude Sonnet 4.6 pricing ($3/1M input, $15/1M output). Cowork and Claude Desktop subscription users (Pro/Max/Team) are not charged per-token — these estimates apply only to direct Anthropic API usage. Running stages individually in fresh sessions uses fewer input tokens than running the full pipeline sequentially, because pipeline mode accumulates conversation history across stages.

Per skill (run individually in a fresh session):

Stage	Skill Prompt	User Input	Total Input	Output	Est. Cost
proposal-draft	~1.7K	~800	~5.1K	~6.0K	~$0.11
proposal-pricing	~1.7K	~800	~5.1K	~3.0K	~$0.06
proposal-structure	~1.5K	~800	~4.9K	~3.0K	~$0.06
proposal-review	~3.2K	~800	~6.7K	~6.0K	~$0.11
proposal-intake	~1.7K	~800	~5.1K	~3.0K	~$0.06
Standalone total			~26.9K	~21.0K	~$0.40

Full pipeline (all stages in one session — context accumulates):

Stage	Base Input	+ History	Total Input	Output	Est. Cost
proposal-draft	~5.4K	0	~5.4K	~6.0K	~$0.11
proposal-pricing	~5.4K	~6.8K	~12.2K	~3.0K	~$0.08
proposal-structure	~5.1K	~10.6K	~15.7K	~3.0K	~$0.09
proposal-review	~6.9K	~14.4K	~21.3K	~6.0K	~$0.15
proposal-intake	~5.3K	~21.2K	~26.5K	~3.0K	~$0.12
Pipeline total			~81.0K	~21.0K	~$0.56

Running the full pipeline once typically costs $0.39–$0.73 in API tokens (Claude Sonnet 4.6).

Known Limitations

No e-signatures: Proposals are DOCX files only. Signing requires external tools (Adobe Sign, DocuSign, HelloSign). Users must print/email the DOCX and collect signatures separately.
No client portal: Proposals are not shareable via a live portal. No tracking of open/read time, editing, or version history. Users send DOCX via email.
No payment integration: Proposals reference payment terms (e.g., "50% upfront") but do not include payment links or buttons. Invoice/payment collection must be handled separately.
No CRM integration: Proposals are standalone. No sync with Salesforce, HubSpot, or other CRMs. Users must manually copy client info to/from CRM.
Single-user only: No multi-user collaboration on proposals. One consultant/sales person, one Claude session. Concurrent edits will cause data loss.
No proposal analytics: No tracking of proposal open rates, read time, or client engagement. All analytics must be managed manually.
No team templates library: Custom templates are stored locally. No centralized template library or team sharing of proposal templates.
Legal compliance scope: Proposals include a legal disclaimer ("for discussion purposes only, subject to signed SOW or contract"). This is a template. Have your legal counsel review the disclaimer language for your jurisdiction.
No multi-currency: All pricing is in a single currency (USD by default, configurable in setup). Multi-currency proposals would require manual adjustment.
No smart merge fields: Unlike Proposify/PandaDoc, this plugin does not support smart merge fields that auto-populate from your CRM or template library. Customization is done via conversational input to Claude.

Requirements

Python 3.8+ with python-docx >= 0.8.11 (auto-installed by /proposal-setup)
Claude with Read, Write, Bash tools enabled
Workspace folder selected in Cowork (or equivalent file access)
Business name: For proposal headers (collected during setup)

Important Disclaimers

AI-Generated Content: This plugin uses AI (LLM) technology which can produce inaccurate or incomplete outputs. All content should be treated as a starting point and reviewed for accuracy before use.
Not Professional Advice: Outputs do not constitute legal, financial, tax, medical, or other professional advice. Consult qualified professionals before making decisions based on generated content.
No Compliance Guarantee: References to industry standards, regulations, or guidelines are for informational purposes only. This plugin does not guarantee compliance with any law or regulation. Users are responsible for verifying all outputs meet their specific regulatory requirements.
No Endorsement or Affiliation: Mention of third-party products, standards, or organizations does not imply endorsement, partnership, or certification by those entities.

Sales Proposal Generator