mizzlelover/gongwen-gbt9704-skill

信息安全提醒：请勿上传企业禁止对外公开的文件；可在本地或企业内网部署大模型后使用。中文公文排版 Skill：按 GB/T 9704-2012 生成可编辑 DOCX。配套 CEB：https://github.com/mizzlelover/CEB

What it solves

It automates the complex and rigid formatting requirements of official Chinese government documents (Gongwen) based on the GB/T 9704-2012 national standard. It eliminates the manual effort of adjusting margins, fonts, line spacing, and page numbering in Word or WPS, ensuring that documents meet strict institutional requirements for submission.

How it works

The project provides a "Skill" (a set of rules and scripts) that can be integrated into various AI coding assistants and LLM platforms. It uses a Node.js generator (generate_gongwen_docx.mjs) to convert Markdown or text input into a professionally formatted DOCX file. The system handles specific layouts for different document types (ordinary reports, formal letters, commands, minutes) and manages technical details like red-header (hongtou) placement, font compatibility, and automatic table of contents generation.

Who it’s for

Professionals in Chinese government agencies, state-owned enterprises, and public institutions who need to produce official documents that strictly adhere to national formatting standards.

Highlights

  • Strict Standard Compliance: Specifically engineered to meet the GB/T 9704-2012 standard, including precise measurements for margins and headers.
  • Multi-Platform Support: Compatible with a wide range of AI tools including Claude Code, Kimi, Trae, and WorkBuddy.
  • Comprehensive Layouts: Supports various formal styles such as red-header digital versions, pre-printed paper layouts, joint issuance, and detached attachments.
  • Built-in Verification: Includes a validator script to check if the generated DOCX file meets the promised formatting parameters.
  • Professional Typography: Manages complex Chinese font requirements (e.g., Xiaobiao Song) and provides warnings when standard fonts are missing.

Related

  • Project
    Gostyan/docx-skill-4-cn-paper

    A toolset for AI Agents to create and edit Word documents following Chinese academic formatting standards, featuring Markdown-to-docx conversion and LaTeX-to-native-formula support.

  • Project
    larashero3-dotcom/lieflat-gongwen

    lieflat‑gongwen is a data‑driven “skill” for Chinese AI agents that lets them generate official government‑style documents (work plans, research reports, party‑building material) by matching statistical style fingerprints extracted from a 1 M‑character corpus. It detects the document type, applies numeric style constraints, builds a skeleton, fills the text with an LLM, and runs a Python self‑check to ensure the output stays within the measured ranges. The repo includes the rule set, example drafts, and a non‑commercial license.

  • Project
    Fokkyp/SoftwareCopyright-Skill

    A coding-agent skill that automatically generates complete Chinese software copyright application materials (application form info, operation manual, and code excerpts) from your real project source code, locally and for free. It handles the official 30/30-page code rule, produces DOCX/TXT files, and lets you confirm every key detail before finalizing — no need to pay third-party document services.

  • Project
    chrisryugj/kordoc

    Kordoc is a powerful document parsing and generation engine that converts complex Korean office formats (HWP, HWPX) and PDFs into structured data or Markdown, enabling AI agents and RAG systems to process them with high layout fidelity.

  • Project
    njzjz/nsfc-agent-skills

    A collection of AI agent skills following the Agent Skills specification to assist researchers in writing, illustrating, and managing literature for NSFC grant applications.