Summary

This project provides a standardized, engineering-driven workbench for Chinese undergraduate theses, integrating project artifacts (code, data, literature) into a traceable, revisable document. It targets students with technical projects needing to meet strict academic formatting and content requirements, streamlining thesis quality and submission.

How It Works

The workbench operationalizes thesis writing via a structured workflow: material collection, path selection, evidence building, writing, and DOCX generation. It offers four DOCX delivery paths: M1 (default generation), M2 (sample-based style approximation), M3 (template copy filling), and M4 (existing draft editing). Path M3 uniquely preserves original template OOXML structures by filling placeholders, making it ideal for schools with rigid formatting rules. Material scarcity is addressed via optional web literature searches or brainstorming sessions.

Quick Start & Requirements

Install Python dependencies: pip install -r requirements.txt. For automated screenshots, install Node.js/Playwright (npm install && npm run install:browsers). Initialize workspace: python scripts/workspace/init_thesis_workspace.py <project_dir>. Configuration involves editing YAML files within assets/thesis-ai-standard/templates/.

Highlighted Details

• Four DOCX Delivery Paths: Offers flexible output options including direct template filling (M3) and precise draft editing (M4).
• Automated Artifact Integration: Generates evidence from code, databases, and APIs; supports automated screenshots for diagrams (Mermaid, PlantUML, draw.io) via Playwright.
• Material Scarcity Mitigation: Handles insufficient source material by suggesting web literature searches or brainstorming sessions with user consent.
• Traceability: Generates control files (e.g., user-dashboard.md, material-inventory.md) for progress tracking and decision logging.

Maintenance & Community

The project references foundational components xiaou61/thesis-skills and Doryoku1223/lunwen-skill. Active development is indicated by versioning (e.g., v1.0.0). No specific community channels or roadmap links are provided in the README.

Licensing & Compatibility

The project is released under the MIT License, which is permissive and generally suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

This tool is primarily for technical theses (software, experiments, research) with existing projects; purely humanities theses may require significant adaptation. It is explicitly positioned as a workbench, not an automated paper generator. Path M4's text editing relies on exact anchor matching, potentially causing errors if anchors are ambiguous or missing. Automated screenshotting requires separate Node.js/Playwright setup.