agentleFS
aiagentwithdhruvaiagentwithdhruv/skills/create-proposal/SKILL.md

create-proposal

Skill16 starsChanged 9 months agoMITView on GitHub

Generate PandaDoc proposals from client information or sales call transcripts. Use when user asks to create a proposal, generate a quote, draft a contract, or prepare a client document.

  • Reads credentials

4 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 7 are common, 0 are distinctive, and 0 are very specific to this project.

  • 7

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

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

    line 9
  2. Common:

    If user provides structured data, use directly

    line 31
  3. Common:

    If user provides transcript, extract:

    line 32
  4. Common:

    Ask for any missing critical information

    line 38
  5. Common:

    Use direct "you" language (not third-person)

    line 44
  6. Common:

    Use Gmail to send HTML follow-up email:

    line 97
  7. Common:

    Follow-up email sent to client

    line 111

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

NameTypeRequiredDescription
client_first_namestringYesClient first name
client_last_namestringYesClient last name
client_emailstringYesClient email address
client_companystringYesClient company name
project_titlestringYesProject title
problemsarrayYes4 key problems (brief)
benefitsarrayYes4 key benefits (brief)
investment_breakdownobjectYesMonth 1, Month 2, Month 3+ pricing
call_transcriptstringNoAlternative: sales call transcript to extract details from

Outputs

NameTypeDescription
pandadoc_urlstringPandaDoc internal link for review
email_sentbooleanWhether follow-up email was sent

Credentials

NameSource
PANDADOC_API_KEY.env

Composable With

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

Cost

PandaDoc API call (free tier available)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.