Skip to main content
Glama

Pharos AI Doc Genie β€” Document Generation Skill

Built for Pharos Skill-to-Agent Dual Cascade Hackathon β€” Phase 1

A reusable, standardized Skill module that enables any AI Agent in the Pharos ecosystem to generate real Office documents (.pptx, .docx, .xlsx) and source code from natural language β€” powered by DashScope LLM API.

License: MIT Node.js MCP


🎯 Problem Statement

AI Agents in the Pharos economy need to produce tangible outputs β€” not just text responses. When an agent helps a user prepare a business proposal, it should deliver a real .docx file. When it analyzes data, it should produce an actual .xlsx spreadsheet. When it creates a presentation, it should output a .pptx that opens in PowerPoint.

Existing solutions either:

  • Generate plain text/Markdown that requires manual formatting

  • Depend on proprietary cloud APIs with unpredictable availability

  • Lack standardized interfaces for agent-to-skill communication

Pharos AI Doc Genie fills this gap with a production-ready, standardized Skill that generates real Office files and code from natural language.


Related MCP server: InkPaw

🧩 Skill Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                AI Agent (Pharos)              β”‚
β”‚         (Any MCP-compatible Agent)            β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                  β”‚ MCP Protocol (JSON-RPC 2.0)
                  β”‚ stdio transport
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚          Pharos AI Doc Genie Skill            β”‚
β”‚                                               β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”      β”‚
β”‚  β”‚ generate β”‚ β”‚ generate β”‚ β”‚ generate β”‚      β”‚
β”‚  β”‚ _word    β”‚ β”‚  _ppt    β”‚ β”‚ _excel   β”‚ ...  β”‚
β”‚  β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”˜      β”‚
β”‚       β”‚            β”‚            β”‚             β”‚
β”‚  β”Œβ”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”      β”‚
β”‚  β”‚        LLM (DashScope qwen)         β”‚      β”‚
β”‚  β”‚    Content Generation Layer         β”‚      β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β”‚
β”‚                   β”‚                            β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”      β”‚
β”‚  β”‚     Python (python-pptx, etc.)      β”‚      β”‚
β”‚  β”‚     File Conversion Layer           β”‚      β”‚
β”‚  β”‚     Markdown β†’ real .pptx/.docx     β”‚      β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                    β”‚
         β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
         β”‚   Output Files      β”‚
         β”‚  .pptx  .docx       β”‚
         β”‚  .xlsx  .py/.js/... β”‚
         β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Key design principles:

  • Stateless: Each tool call is independent β€” no session state needed

  • Idempotent: Same input produces consistent output structure

  • Self-contained: Zero external service dependencies beyond the LLM API

  • Standardized: MCP protocol ensures any compatible Agent can call it


πŸ› οΈ Tools (4 Skills)

Tool

Output

Use Case

Model

generate_ppt

.pptx presentation

Pitch decks, training, reports

qwen3.7-plus

generate_word

.docx document

Proposals, manuals, reports

qwen3.7-plus

generate_excel

.xlsx spreadsheet

Data tables, financials, inventory

qwen3.7-plus

generate_code

Source code (.py/.js/.go/...)

Rapid prototyping, boilerplate

qwen-long-latest

Tool Schema Examples

generate_ppt: Create a professional presentation

{
  "name": "generate_ppt",
  "arguments": {
    "topic": "AI in Enterprise: 2026 Trends",
    "requirements": "Executive summary for CTO audience, 12 slides, focus on ROI and adoption metrics",
    "slide_count": 12
  }
}

generate_excel: Generate structured data

{
  "name": "generate_excel",
  "arguments": {
    "description": "Q2 2026 sales data: Region, Product Category, Revenue, Units Sold, Growth%, Top Salesperson",
    "rows": 30
  }
}

πŸš€ Quick Start

Prerequisites

  • Node.js >= 18

  • Python 3.8+ with python-pptx, python-docx, openpyxl

  • DashScope API Key (Alibaba BaiLian)

Install Python dependencies

pip install python-pptx python-docx openpyxl

Run the MCP Server

node src/mcp-server.js

The server listens on stdin/stdout using the MCP stdio transport. Configure your Agent's MCP client to launch this process.

Test with MCP Inspector

npx @modelcontextprotocol/inspector node src/mcp-server.js

Manual Test (JSON-RPC via pipe)

echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | node src/mcp-server.js

πŸ“ Project Structure

pharos-ai-doc-genie/
β”œβ”€β”€ src/
β”‚   └── mcp-server.js       # MCP stdio server (self-contained)
β”œβ”€β”€ convert.py               # Python: Markdown β†’ .pptx/.docx/.xlsx
β”œβ”€β”€ output/                  # Generated Office files
β”œβ”€β”€ package.json             # Node.js project config
β”œβ”€β”€ README.md                # This file
β”œβ”€β”€ LICENSE                  # MIT License
└── .gitignore

πŸ”Œ Integration

With Claude Desktop

{
  "mcpServers": {
    "pharos-ai-doc-genie": {
      "command": "node",
      "args": ["/absolute/path/to/pharos-ai-doc-genie/src/mcp-server.js"]
    }
  }
}

With OpenAI Agents

The server uses standard MCP tool schemas that are directly compatible with OpenAI function calling format. Simply configure your Agent to launch the server as an MCP subprocess.

With Pharos Agents

Pharos Agents can call this Skill via the MCP protocol. Once the Skill is registered, Agents discover it through tools/list and call it through tools/call.


πŸ§ͺ Testing

# List available tools
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | node src/mcp-server.js

# Generate a Word document
echo '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"generate_word","arguments":{"topic":"Project Proposal: AI Chatbot","requirements":"A formal proposal for building an enterprise AI chatbot. Include: executive summary, technical approach, timeline, budget estimate.","length":"medium"}}}' | node src/mcp-server.js

# Generate code
echo '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"generate_code","arguments":{"requirement":"A Python async function that fetches data from a REST API with exponential backoff retry logic","language":"python","comments":"en"}}}' | node src/mcp-server.js

⚑ Performance

Tool

Avg. Response Time

Max Tokens

File Size

generate_word

~20-40s

16384

30-50 KB (.docx)

generate_ppt

~30-60s

16384

25-40 KB (.pptx)

generate_excel

~15-25s

16384

5-15 KB (.xlsx)

generate_code

~15-30s

16384

N/A (text)


πŸ”’ Security

  • No API key exposure: The DashScope API key is server-side only and never sent to Agents

  • Input validation: All Agent inputs are validated before processing

  • Output isolation: Generated files are written to a dedicated output directory

  • No persistent state: Each tool call is isolated with no cross-call data leakage


πŸ—ΊοΈ Roadmap

Phase 2 (Agent Arena)

  • Deploy as a persistent Skill on Pharos chain

  • On-chain billing per document generation

  • NFT-based document ownership and verification

  • Multi-agent collaborative document editing

Beyond

  • PDF generation and manipulation

  • Image-to-document conversion (OCR β†’ formatted docx)

  • Multi-language document templates

  • Real-time collaborative editing via WebSocket


πŸ‘€ Author

huimingchen081-beep (GitHub)

Built for the Pharos Skill-to-Agent Dual Cascade Hackathon β€” Phase 1 (Skill Hackathon).


πŸ“„ License

MIT License β€” see LICENSE for details.


πŸ™ Acknowledgments

  • Pharos Network β€” for building the AI Agent economy infrastructure

  • DashScope (Alibaba BaiLian) β€” for the LLM API powering content generation

  • Model Context Protocol (Anthropic) β€” for the standardized agent-skill communication protocol

  • python-pptx / python-docx / openpyxl β€” for Office file generation

Available Tools

4 tools
generate_codeA

Generate production-ready source code in any programming language from natural language requirements. The AI writes complete, well-commented code following best practices and naming conventions. Use this for rapid prototyping, boilerplate generation, or educational examples.

Inputs: requirement (required), language (required), comments.

generate_excelA

Generate a structured data spreadsheet (.xlsx) from natural language description. The AI creates realistic, well-formatted data tables with proper headers and data rows. Use this for financial statements, sales data, inventory lists, or any tabular data.

Inputs: description (required), rows.

generate_pptA

Generate a professional PowerPoint presentation (.pptx) from natural language. The AI creates structured slide content with titles, bullet points, and visual suggestions. Use this when you need presentation slides, pitch decks, or training materials.

Inputs: topic (required), requirements (required), slide_count.

generate_wordA

Generate a complete Word document (.docx) from natural language. The AI creates well-structured content with headings, paragraphs, bullet points, and proper formatting. Use this for proposals, reports, meeting minutes, manuals, or any formal document.

Inputs: topic (required), requirements (required), length.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool generates a distinct type of output (code, spreadsheet, presentation, word document), making them easily distinguishable. There is no overlap in purpose or output format.

    Naming Consistency5/5

    All tools follow a consistent 'generate_' prefix pattern, making the naming uniform and predictable. The verb 'generate' is appropriate for the creation-oriented domain.

    Tool Count5/5

    With only 4 tools, the set is tightly scoped to common file generation tasks. Each tool serves a clear, non-redundant purpose, and the count is well-suited for a specialized server.

    Completeness4/5

    The set covers the most common generation needs (code, Excel, PowerPoint, Word). Minor gaps like PDF or CSV generation exist, but these are not critical for the core use case.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      Enables complete Office document lifecycle management for AI agents, including creation, editing, conversion, and templating of DOCX, XLSX, PPTX, PDF, and EML files.
      40
      55 PyPI
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to generate, edit, validate, and render Word documents programmatically via MCP, ensuring correct OOXML structure and style.
      3
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to create and process office documents locally, including generating branded PDF, Word, Excel, and editable PowerPoint files from templates and themes, plus reading, OCR, form-filling, manipulation, and conversion of PDFs.
      1
      MIT