Create Proposal

Proposal Generation

Goal

Create PandaDoc proposals for clients, either from structured information or by extracting details from sales call transcripts.

Inputs (One of the following)

Option A: Structured Data

• Client First Name, Last Name, Email, Company
• Project Title
• 4 Key Problems (brief)
• 4 Key Benefits (brief)
• Project Duration
• Investment Breakdown (Month 1, Month 2, Month 3+)

Option B: Call Transcript

• Sales call transcript to extract all details from

Scripts

• ./scripts/create_proposal.py - Creates PandaDoc proposal via API
• ./scripts/read_sheet.py - Read client data from sheets if needed

Process

1. Gather Information

• If user provides structured data, use directly
• If user provides transcript, extract:
• Client info (name, company, email)
• Project context and title
• 4 main problems/pain points
• 4 proposed solutions/benefits
• Financial terms (duration, value, costs)
• Ask for any missing critical information

2. Generate Content

Expand the 4 problems and 4 benefits into strategic paragraphs:

Problem Expansion Guidelines:

• Use direct "you" language (not third-person)
• Focus on revenue impact and dollar amounts
• Be specific and actionable
• Example: "Right now, your top-of-funnel is converting very poorly to booked meetings..."

Benefit Expansion Guidelines:

• Address the client directly
• Emphasize ROI and payback period
• Focus on concrete deliverables

Also generate:

• Slide Footer: "Confidential | [Company] Strategic Initiative | [Date]"
• Contract Footer: "[Company]-[ProjectTitle]-[YYYY-MM]"
• Created Date: Current date (YYYY-MM-DD)

3. Execute Proposal Creation

python3 ./scripts/create_proposal.py <<'EOF'
{
  "client": {
    "firstName": "...",
    "lastName": "...",
    "email": "...",
    "company": "..."
  },
  "project": {
    "title": "...",
    "problems": {
      "problem01": "[Expanded Problem 1]",
      "problem02": "[Expanded Problem 2]",
      "problem03": "[Expanded Problem 3]",
      "problem04": "[Expanded Problem 4]"
    },
    "benefits": {
      "benefit01": "[Expanded Benefit 1]",
      "benefit02": "[Expanded Benefit 2]",
      "benefit03": "[Expanded Benefit 3]",
      "benefit04": "[Expanded Benefit 4]"
    },
    "monthOneInvestment": "...",
    "monthTwoInvestment": "...",
    "monthThreeInvestment": "..."
  },
  "generated": {
    "slideFooter": "...",
    "contractFooterSlug": "...",
    "createdDate": "..."
  }
}
EOF

4. Send Follow-Up Email

Use Gmail to send HTML follow-up email:

• Subject: "Re: [Brief Project Context] Discussion"
• Opening: Thank them for discussing challenges
• Body: 2-4 numbered sections with bold headers
• Each section: Description + "Steps:" bullet points
• Closing: "I'll send you a full proposal shortly..."
• Signature: "Thanks, Nick"

5. Notify User

• Provide the PandaDoc "internalLink" for review
• Confirm follow-up email was sent

Output

• PandaDoc proposal URL (for editing/review)
• Follow-up email sent to client

Environment

Requires in .env:

PANDADOC_API_KEY=your_key

---

Schema

Inputs

| Name | Type | Required | Description | |------|------|----------|-------------| | client_first_name | string | Yes | Client first name | | client_last_name | string | Yes | Client last name | | client_email | string | Yes | Client email address | | client_company | string | Yes | Client company name | | project_title | string | Yes | Project title | | problems | array | Yes | 4 key problems (brief) | | benefits | array | Yes | 4 key benefits (brief) | | investment_breakdown | object | Yes | Month 1, Month 2, Month 3+ pricing | | call_transcript | string | No | Alternative: sales call transcript to extract details from |

Outputs

| Name | Type | Description | |------|------|-------------| | pandadoc_url | string | PandaDoc internal link for review | | email_sent | boolean | Whether follow-up email was sent |

Credentials

| Name | Source | |------|--------| | PANDADOC_API_KEY | .env |

Composable With

Skills that chain well with this one: onboarding-kickoff, welcome-email

Cost

PandaDoc API call (free tier available)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: aiagentwithdhruv
• Source: aiagentwithdhruv/skills
• License: MIT

Install and usage instructions live in the source repository linked above.