Word Document Reader and Writer
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
Converts a tender document into Markdown, extracts scoring criteria and requirements, then drafts an industry-formatted technical bid as a Word file.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Get00/BiaoShu-SKILL bid-writer-pro --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Get00/BiaoShu-SKILL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/BiaoShu-writer-pro .claude/skills/bid-writer-pro && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bid-writer-pro" agent skill from https://github.com/Get00/BiaoShu-SKILL/tree/main/BiaoShu-writer-pro into .claude/skills/bid-writer-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bid-writer-pro", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Get00/BiaoShu-SKILL/tree/main/BiaoShu-writer-proType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Get00/BiaoShu-SKILL bid-writer-pro --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Get00/BiaoShu-SKILL.git skills-src && mkdir -p .agents/skills && cp -r skills-src/BiaoShu-writer-pro .agents/skills/bid-writer-pro && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bid-writer-pro" agent skill from https://github.com/Get00/BiaoShu-SKILL/tree/main/BiaoShu-writer-pro into .agents/skills/bid-writer-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bid-writer-pro", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Get00/BiaoShu-SKILL bid-writer-pro --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Get00/BiaoShu-SKILL.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/BiaoShu-writer-pro .cursor/skills/bid-writer-pro && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bid-writer-pro" agent skill from https://github.com/Get00/BiaoShu-SKILL/tree/main/BiaoShu-writer-pro into .cursor/skills/bid-writer-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bid-writer-pro", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Get00/BiaoShu-SKILL.git --path BiaoShu-writer-pro--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Get00/BiaoShu-SKILL bid-writer-pro --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Get00/BiaoShu-SKILL.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/BiaoShu-writer-pro .gemini/skills/bid-writer-pro && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bid-writer-pro" agent skill from https://github.com/Get00/BiaoShu-SKILL/tree/main/BiaoShu-writer-pro into .gemini/skills/bid-writer-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bid-writer-pro", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Get00/BiaoShu-SKILL bid-writer-proInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Get00/BiaoShu-SKILL.git skills-src && mkdir -p .github/skills && cp -r skills-src/BiaoShu-writer-pro .github/skills/bid-writer-pro && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bid-writer-pro" agent skill from https://github.com/Get00/BiaoShu-SKILL/tree/main/BiaoShu-writer-pro into .github/skills/bid-writer-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bid-writer-pro", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Get00/BiaoShu-SKILL bid-writer-pro --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Get00/BiaoShu-SKILL.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/BiaoShu-writer-pro .opencode/skills/bid-writer-pro && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bid-writer-pro" agent skill from https://github.com/Get00/BiaoShu-SKILL/tree/main/BiaoShu-writer-pro into .opencode/skills/bid-writer-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bid-writer-pro", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
bid-writer-proConverts a tender document into Markdown, extracts scoring criteria and requirements, then drafts an industry-formatted technical bid as a Word file.
Written in Chinese, this skill automates the technical part of a bid document. You send a tender file in PDF, DOCX, DOC, TXT or XLSX form, and the tool converts it to Markdown, detects which industry it belongs to, extracts scoring items, weights and key qualification, technical and commercial requirements, and pulls out the project name.
From the scoring standard it builds a four-level outline, waits for your confirmation, then writes the sections concurrently, checks word counts by formula, removes traces of AI-sounding phrasing, and marks places where images, tables or qualification documents must be inserted. The output is a Word file named after the project with a technical-bid suffix, in a timestamped folder for each run.
Supported industries are IT, construction, medical, education, manufacturing, logistics and consulting, plus a general template. When an unfamiliar industry appears, the skill can create a new industry guide. A Python pipeline script, an environment checker and format-conversion scripts back the process, and SimSun, SimHei and FangSong fonts are expected for standard formatting.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 23ec3ae. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 14 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythonpipFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Industry Bid Document Writer loads about 4.6k tokens when it runs, and up to ~6.5k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 611 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from Get00/BiaoShu-SKILL at commit 23ec3ae, republished under its Apache-2.0 licence (© Get00). 611 words, ~4,602 tokens.
.claude/skills/bid-writer-pro/SKILL.md (or your agent's skills folder). This skill also uses 54 other files; get the full folder from GitHub.投标技术标文档自动生成工具。发送招标文件 → 自动转换Markdown → 生成符合行业标准格式的Word标书文档。
debug/bid_document.md,便于查看{项目名称}技术标.docxpip install python-docx pdfplumber openpyxl PyPDF2 jieba pandas pywin32将字体文件复制到系统字体目录:
C:\Windows\Fonts\~/Library/Fonts/# 1. 发送招标文件(PDF/DOCX)给AI
# 2. AI自动解析并生成大纲
# 3. 确认大纲后AI并发编写各章节
# 4. 字数检查 + AI去痕处理
# 5. 生成占位符标记
# 6. 转换生成Word文档# 完整流程
python scripts/bid_writer_pipeline.py "招标文件.pdf" --output-dir ./output
# 带企业资质信息
python scripts/bid_writer_pipeline.py "招标文件.docx" \
--company-profile "企业资质.json" \
--output-dir ./标书输出
# 指定格式标准
python scripts/bid_writer_pipeline.py "招标文件.pdf" \
--format-standard government \
--output-dir ./output# 直接导入使用
import sys
sys.path.insert(0, '/path/to/bid-writer-pro/scripts')
from bid_writer_pipeline import BidWriterPipeline
pipeline = BidWriterPipeline(
bid_file="招标文件.pdf",
output_dir="./output",
format_standard="government"
)
result = pipeline.run()# 检查环境是否满足要求
python scripts/check_environment.py
# 安装依赖库
python install.py
# 或直接使用pip
pip install -r requirements.txt通读模板知识 → 发送招标文件 → 转换Markdown → 解析评分标准 → 提取标书名称 → 生成大纲 →
确认大纲 → 并发编写章节 → 字数检查 → AI去痕 →
占位符生成 → 转换Word → 格式规范化 → 输出标书.docx在开始撰写标书之前,必须先判断招标文件所属的行业类型,这是生成高质量标书的关键步骤!
第1步:读取招标文件内容
↓
第2步:AI分析招标文件,判断所属行业
↓
第3步:检查templates文件夹中是否存在该行业的指南文件
↓
┌─ 如果存在:industry_{行业名称}.md
│ └─ 按照行业指南执行,生成符合行业特点的标书
│
└─ 如果不存在:
└─ AI进行互联网检索,收集该行业的:
- 行业特点和规范
- 投标文件结构要求
- 关键内容要点
- 评分标准关注点
↓
└─ 自动生成 industry_{行业名称}.md 文件
↓
└─ 保存到 templates 文件夹
↓
└─ 告知用户:已创建新的行业指南,SKILL已完善| 行业代码 | 行业名称 | 指南文件 |
|---|---|---|
| it_information | IT/信息化 | 00_标书制作指南.md |
| construction | 建筑工程 | industry_建筑工程.md |
| medical | 医疗健康 | industry_医疗健康.md |
| education | 教育服务 | industry_教育服务.md |
| manufacturing | 制造业 | industry_制造业.md |
| logistics | 物流运输 | industry_物流运输.md |
| consulting | 咨询服务 | industry_咨询服务.md |
| general | 通用行业 | 00_标书制作指南.md |
IT/信息化:信息化、软件、系统集成、数据中心、云计算、大数据、人工智能、数字化 建筑工程:建筑、施工、工程、装修、市政、道路、桥梁、隧道 医疗健康:医疗、健康、医院、设备、药品、诊断、治疗、康复 教育服务:教育、学校、教学、培训、校园、课程、实验室、图书馆 制造业:制造、设备、自动化、智能制造、工业、生产线、供应链、质量 物流运输:物流、运输、仓储、配送、供应链、快递、货运、冷链 咨询服务:咨询、管理、审计、法律、评估、规划、研究、策划
示例1:招标文件中包含"智慧交通"、"系统集成"、"软件开发" → 判断为:IT/信息化 → 使用指南:00_标书制作指南.md
示例2:招标文件中包含"医院"、"医疗设备"、"诊断" → 判断为:医疗健康 → 使用指南:industry_医疗健康.md
示例3:招标文件中包含"建筑工程"、"施工"、"装修" → 判断为:建筑工程 → 使用指南:industry_建筑工程.md
在判断行业类型后,必须通读 templates 文件夹中的相关行业指南,包括:
00_标书制作指南.md - 标书制作的通用指南industry_{行业名称}.md - 特定行业的投标指南(如果存在)bid_doc_*.md - 从DOC/DOCX转换的标书知识文档bid_knowledge_*.md - 从PDF转换的招投标知识文档通读目的:
templates 文件夹中是否存在该行业的指南文件debug/bid_document.md{项目名称}技术标.docx在开始执行前,先根据用户需求选择路径:
用户需求是什么?
│
├─ 【完整生成标书】有招标文件,想生成完整标书
│ └─ 运行完整流程:scripts/bid_writer_pipeline.py "招标文件.pdf" --output-dir ./output
│ └─ 自动执行14个步骤:通读模板 → 解析文件 → 提取评分 → 生成大纲 → 生成内容 → 字数检查 → AI去痕 → 生成Word
│
├─ 【仅解析招标文件】只想提取招标文件中的信息
│ └─ 运行 scripts/parse_bid_file.py "招标文件.pdf"
│ └─ 输出:文本内容、评分标准、关键要求
│
├─ 【转换文档格式】想把PDF/DOCX转换为Markdown
│ ├─ 转换单个文件:运行 scripts/convert_to_md.py "文件.pdf" --output "输出.md"
│ ├─ 批量转换PDF:运行 scripts/convert_pdf_to_md.py --source "PDF文件夹" --output "输出文件夹"
│ └─ 批量转换DOC/DOCX:运行 scripts/convert_doc_to_md.py --source "DOC文件夹" --output "输出文件夹"
│
├─ 【仅提取评分标准】只想分析招标文件的评分标准
│ └─ 运行 scripts/extract_scoring.py "招标文件内容.txt"
│ └─ 输出:scoring_criteria.json(评分大类、分值、权重)
│
├─ 【仅提取关键要求】只想提取资质、技术、商务要求
│ └─ 运行 scripts/extract_requirements.py "招标文件内容.txt"
│ └─ 输出:key_requirements.json(资质要求、技术要求、商务要求)
│
├─ 【仅生成大纲】已有评分标准,想生成标书大纲
│ └─ 运行 scripts/generate_outline.py --scoring "scoring_criteria.json"
│ └─ 输出:outline.json(4级标题大纲、字数分配)
│
├─ 【仅生成内容】已有大纲,想生成标书内容
│ └─ 运行 scripts/generate_content.py --outline "outline.json" --scoring "scoring_criteria.json"
│ └─ 输出:各章节Markdown文件
│
├─ 【检查字数】已有内容,想检查字数是否达标
│ └─ 运行 scripts/check_word_count.py --chapters "chapters文件夹" --scoring "scoring_criteria.json"
│ └─ 输出:字数检查报告(目标字数、实际字数、是否达标)
│
├─ 【AI去痕处理】已有内容,想去除AI生成痕迹
│ └─ 运行 scripts/humanizer.py --input "内容.md" --output "处理后.md"
│ └─ 输出:去痕后的自然语言内容
│
├─ 【生成占位符】已有内容,想标记图片/表格/资质位置
│ └─ 运行 scripts/generate_placeholder.py --chapters "chapters文件夹" --requirements "key_requirements.json"
│ └─ 输出:带占位符标记的内容
│
├─ 【Markdown转Word】已有Markdown内容,想生成Word文档
│ └─ 运行 scripts/convert_to_docx.py --input "内容.md" --output "标书.docx" --standard government
│ └─ 输出:符合行业标准格式的Word文档
│
├─ 【格式规范化】已有Word文档,想统一格式
│ └─ 运行 scripts/format_docx.py --input "标书.docx" --standard government
│ └─ 输出:格式规范化的Word文档
│
├─ 【生成封面】想为标书生成封面页
│ └─ 运行 scripts/generate_cover.py --name "项目名称" --requirements "key_requirements.json"
│ └─ 输出:封面页Markdown
│
├─ 【生成目录】想为标书生成目录页
│ └─ 运行 scripts/generate_toc.py --chapters "chapters文件夹"
│ └─ 输出:目录页Markdown
│
├─ 【检查环境】想检查运行环境是否满足要求
│ └─ 运行 scripts/check_environment.py
│ └─ 输出:环境检查报告(Python版本、依赖库、脚本文件、模板知识)
│
├─ 【构建模板知识库】想从标书范本中提取知识
│ ├─ 从DOC/DOCX提取:运行 scripts/extract_templates.py --source "范本文件夹" --output "templates文件夹"
│ └─ 从PDF提取:运行 scripts/convert_pdf_to_md.py --source "PDF文件夹" --output "templates文件夹"
│
├─ 【查看中间结果】想查看已生成的中间文件
│ ├─ 查看评分标准:打开 output/scoring_criteria.json
│ ├─ 查看关键要求:打开 output/key_requirements.json
│ ├─ 查看大纲:打开 output/outline.json
│ ├─ 查看章节内容:打开 output/chapters/*.md
│ └─ 查看调试信息:打开 output/debug/ 文件夹
│
└─ 【需求不清楚或包含多步】不确定需要什么
└─ 运行完整流程:scripts/bid_writer_pipeline.py "招标文件.pdf" --output-dir ./output
└─ 自动执行所有步骤,生成完整标书# 用户有招标文件,想生成完整标书
python scripts/bid_writer_pipeline.py "XX市智慧交通项目招标文件.pdf" --output-dir ./output自动执行:通读模板 → 解析文件 → 提取评分 → 提取要求 → 提取名称 → 生成大纲 → 生成内容 → 字数检查 → AI去痕 → 占位符 → 封面 → 目录 → 生成Word → 格式规范化
# 步骤1:解析招标文件
python scripts/parse_bid_file.py "招标文件.pdf" --output "bid_content.txt"
# 步骤2:提取评分标准
python scripts/extract_scoring.py --input "bid_content.txt" --output "scoring_criteria.json"
# 步骤3:提取关键要求
python scripts/extract_requirements.py --input "bid_content.txt" --output "key_requirements.json"
# 步骤4:生成大纲(可人工审核调整)
python scripts/generate_outline.py --scoring "scoring_criteria.json" --requirements "key_requirements.json" --output "outline.json"
# 步骤5:生成内容
python scripts/generate_content.py --outline "outline.json" --scoring "scoring_criteria.json" --output-dir "./chapters"
# 步骤6:字数检查
python scripts/check_word_count.py --chapters "./chapters" --scoring "scoring_criteria.json"
# 步骤7:AI去痕
python scripts/humanizer.py --input-dir "./chapters" --output-dir "./chapters_humanized"
# 步骤8:生成Word
python scripts/convert_to_docx.py --input-dir "./chapters_humanized" --output "标书.docx" --standard government# 将PDF转换为Markdown
python scripts/convert_to_md.py "招标文件.pdf" --output "招标文件.md"
# 批量转换PDF文件夹
python scripts/convert_pdf_to_md.py --source "./pdf_files" --output "./markdown_files"
# 批量转换DOC/DOCX文件夹
python scripts/convert_doc_to_md.py --source "./doc_files" --output "./markdown_files"# 已有Word文档,统一格式
python scripts/format_docx.py --input "标书.docx" --standard government --output "标书_规范化.docx"# 检查运行环境是否满足要求
python scripts/check_environment.pyscripts/check_environment.py 检查环境python install.py --auto 或 pip install -r requirements.txttemplates 文件夹中有知识文档government(政府标准)、enterprise(企业标准)、highway(高速公路标准)output/debug/ 文件夹,便于调试和审核[图片占位符]
类型:技术架构图
描述:XX系统总体架构图
建议尺寸:宽15cm × 高10cm[表格占位符]
类型:项目业绩表
描述:近3年类似项目清单
建议列数:6列
建议内容:项目名称、合同金额、完成时间、项目规模、客户名称、验收情况[资质占位符]
类型:企业资质证书
描述:信息系统集成及服务一级资质证书
要求:有效期内的彩色扫描件| 类型 | 占位符内容 | 使用场景 |
|---|---|---|
| 图片 | [图片占位符] 类型:技术架构图 | 技术方案章节 |
| 图片 | [图片占位符] 类型:网络拓扑图 | 网络设计章节 |
| 图片 | [图片占位符] 类型:业务流程图 | 业务流程章节 |
| 表格 | [表格占位符] 类型:功能模块清单 | 功能设计章节 |
| 表格 | [表格占位符] 类型:项目进度计划表 | 项目实施章节 |
| 表格 | [表格占位符] 类型:人员配置表 | 项目团队章节 |
| 表格 | [表格占位符] 类型:项目业绩表 | 项目经验章节 |
| 资质 | [资质占位符] 类型:企业营业执照 | 附件章节 |
| 资质 | [资质占位符] 类型:信息系统集成一级资质 | 附件章节 |
| 资质 | [资质占位符] 类型:ISO9001认证证书 | 附件章节 |
| 资质 | [资质占位符] 类型:项目经理PMP证书 | 附件章节 |
| 元素 | 格式要求 |
|---|---|
| 正文字体 | 仿宋_GB2312 |
| 正文字号 | 四号(14pt) |
| 行距 | 28磅 |
| 页边距 | 上下2.54cm,左右3.17cm |
| 首行缩进 | 2字符 |
| 一级标题 | 黑体、三号(16pt)、加粗 |
| 二级标题 | 黑体、小三(15pt)、加粗 |
| 三级标题 | 黑体、四号(14pt)、加粗 |
| 四级标题 | 仿宋_GB2312、四号(14pt)、加粗 |
| 元素 | 格式要求 |
|---|---|
| 正文字体 | 宋体 |
| 正文字号 | 小四(12pt) |
| 行距 | 1.5倍行距 |
| 页边距 | 上下2.54cm,左右2.54cm |
| 首行缩进 | 2字符 |
| 一级标题 | 黑体、小二(18pt)、加粗 |
| 二级标题 | 黑体、三号(16pt)、加粗 |
| 三级标题 | 黑体、小三(15pt)、加粗 |
| 元素 | 格式要求 |
|---|---|
| 正文字体 | 宋体 |
| 正文字号 | 三号(16pt) |
| 行距 | 28磅 |
| 页边距 | 上下2.5cm,左右2.5cm |
| 首行缩进 | 2字符 |
# 第一章 项目概述
## 1.1 项目背景
### 1.1.1 建设背景
### 1.1.2 现状分析
## 1.2 项目目标
## 1.3 项目范围
# 第二章 技术方案
## 2.1 总体架构
### 2.1.1 架构设计原则
### 2.1.2 系统架构设计
## 2.2 功能设计
### 2.2.1 功能模块划分
### 2.2.2 功能详细说明
## 2.3 数据设计
## 2.4 安全设计
# 第三章 项目实施
## 3.1 实施计划
## 3.2 人员配置
## 3.3 质量保证
## 3.4 风险控制
# 第四章 项目业绩
## 4.1 类似项目经验
## 4.2 客户评价
# 第五章 售后服务
## 5.1 服务体系
## 5.2 响应时间
## 5.3 培训计划
# 附件
## 附件1 企业资质
## 附件2 人员证书
## 附件3 项目业绩证明| 脚本 | 功能 | 输入 | 输出 |
|---|---|---|---|
bid_writer_pipeline.py | 主流程脚本 | 招标文件 | 标书.docx |
parse_bid_file.py | 招标文件解析 | PDF/DOCX/DOC/TXT/XLSX | 文本内容 |
convert_to_md.py | 文档转Markdown | PDF/DOCX/DOC/TXT | Markdown文件 |
extract_scoring.py | 评分标准提取 | 招标文件文本 | scoring_criteria.json |
extract_requirements.py | 关键要求提取 | 招标文件文本 | key_requirements.json |
extract_bid_name.py | 标书名称提取 | 招标文件 | 标书名称.docx |
generate_outline.py | 大纲生成 | 评分标准 | outline.json |
generate_content.py | 内容生成 | 大纲+评分标准 | Markdown内容 |
check_word_count.py | 字数检查 | Markdown内容 | 检查结果 |
humanizer.py | AI去痕处理 | Markdown内容 | 处理后内容 |
convert_to_docx.py | Markdown转Word | Markdown文件 | Word文档 |
convert_pdf_to_md.py | PDF转Markdown | PDF文件夹 | Markdown文件 |
convert_doc_to_md.py | DOC/DOCX转Markdown | DOC/DOCX文件夹 | Markdown文件 |
format_docx.py | Word格式规范化 | Word文档 | 格式化后的Word文档 |
generate_placeholder.py | 占位符生成 | 内容分析 | 占位符标记 |
generate_cover.py | 封面生成 | 项目信息 | 封面页 |
generate_toc.py | 目录生成 | 文档结构 | 目录页 |
check_environment.py | 环境检查工具 | 无 | 检查报告 |
extract_templates.py | 模板提取工具 | DOC/DOCX文件夹 | Markdown文件 |
bid-writer-pro/
├── SKILL.md # 说明文档
├── _meta.json # 元数据配置
├── requirements.txt # 依赖库列表
├── install.py # 安装脚本
├── scripts/ # 脚本目录
│ ├── __init__.py # 包初始化
│ ├── bid_writer_pipeline.py # 主流程脚本
│ ├── parse_bid_file.py # 招标文件解析
│ ├── convert_to_md.py # 文档转Markdown
│ ├── convert_pdf_to_md.py # PDF转Markdown工具
│ ├── convert_doc_to_md.py # DOC/DOCX转Markdown工具
│ ├── extract_scoring.py # 评分标准提取
│ ├── extract_requirements.py # 关键要求提取
│ ├── extract_bid_name.py # 标书名称提取
│ ├── generate_outline.py # 大纲生成
│ ├── generate_content.py # 内容生成
│ ├── check_word_count.py # 字数检查
│ ├── humanizer.py # AI去痕处理
│ ├── convert_to_docx.py # Markdown转Word
│ ├── format_docx.py # Word格式规范化
│ ├── generate_placeholder.py # 占位符生成
│ ├── generate_cover.py # 封面生成
│ ├── generate_toc.py # 目录生成
│ ├── check_environment.py # 环境检查工具
│ └── extract_templates.py # 模板提取工具
└── templates/ # ⭐ 模板知识文件夹(必读)
├── 00_标书制作指南.md # 标书制作完整指南
├── bid_doc_*.md # 标书知识文档(15个)
└── bid_knowledge_*.md # 招投标知识文档(5个)招标文件所在目录/
├── 招标文件.pdf # 原始招标文件
└── XX市智慧交通建设项目技术标.docx # ⭐ 最终标书文件(与招标文件同目录)
output/ # 中间文件目录
└── {时间戳}_{招标文件名}/ # ⭐ 带时间戳的独立文件夹(避免混乱)
│ # 示例:20260522_143025_XX项目招标/
└── debug/ # 所有中间文件保存在debug文件夹
├── template_knowledge.md # 模板知识(通读内容)
├── bid_document.md # 招标文件Markdown版本
├── raw_bid_content.txt # 原始解析内容
├── industry_detection.json # ⭐ 行业检测结果
├── scoring_criteria.json # 评分标准
├── key_requirements.json # 关键要求
├── outline.json # 标书大纲
├── word_count_check.json # 字数检查结果
└── chapters/ # 章节Markdown文件
├── 00_封面.md # 封面
├── 00_目录.md # 目录
├── 01_项目概述.md
├── 02_技术方案.md
├── 03_项目实施.md
├── 04_项目业绩.md
└── 05_售后服务.md{YYYYMMDD}_{HHMMSS}_{招标文件名}20260522_143025_XX市智慧交通项目招标--output-dir 目录下自动创建# 用户发送招标文件
python scripts/bid_writer_pipeline.py "XX市智慧交通项目招标文件.pdf"
# AI处理流程:
# 1. 解析招标文件... ✅
# 2. 提取评分标准... ✅ (技术60分,商务20分,报价20分)
# 3. 提取标书名称... ✅ (XX市智慧交通建设项目技术标.docx)
# 4. 生成大纲... ✅ (5章18节)
# 5. 确认大纲... ✅
# 6. 生成内容... ✅ (约25000字)
# 7. 字数检查... ✅
# 8. AI去痕... ✅
# 9. 生成占位符... ✅ (12个图片,8个表格,6个资质)
# 10. 生成Word... ✅
# 输出文件:XX市智慧交通建设项目技术标.docxpython scripts/bid_writer_pipeline.py "招标文件.docx" \
--company-profile "company_profile.json" \
--format-standard government \
--output-dir ./标书输出# 使用政府标书标准
python scripts/bid_writer_pipeline.py "招标文件.pdf" --format-standard government
# 使用企业标书标准
python scripts/bid_writer_pipeline.py "招标文件.pdf" --format-standard enterprise
# 使用高速公路标准
python scripts/bid_writer_pipeline.py "招标文件.pdf" --format-standard highway查看占位符清单
[图片占位符]、[表格占位符]、[资质占位符]准备素材
替换占位符
最终检查
| 版本 | 日期 | 更新内容 |
|---|---|---|
| v2.2 | 2026-05-22 | 修复输出目录结构:明确时间戳文件夹说明、修复封面和目录保存路径 |
| v2.1 | 2026-05-22 | 添加行业指南自动创建功能:如果行业指南不存在,AI自动检索并创建,逐步完善SKILL |
| v2.0 | 2026-05-22 | 改造为通用行业版:支持8个行业、自动行业检测、行业特定内容生成 |
| v1.9 | 2026-05-21 | 优化内容生成逻辑(更详细丰富)、中间文件保存到debug文件夹、最终标书与招标文件同目录 |
| v1.8 | 2026-05-21 | 修复PDF转换编码问题,添加fix_encoding函数自动检测和修复乱码 |
| v1.7 | 2026-05-21 | 添加详细的任务决策树,包含18种场景和分步执行指南 |
| v1.6 | 2026-05-21 | 修复所有脚本的编码设置问题,避免I/O错误 |
| v1.5 | 2026-05-21 | 删除README.md(避免干扰Trea导入)、精简文件结构 |
| v1.4 | 2026-05-21 | 清理无用文件(删除references文件夹、pycache)、整理md文档、更新文档结构 |
| v1.3 | 2026-05-21 | 新增DOC/DOCX转Markdown功能、扩展templates知识库(包含45个DOC/DOCX转换的知识文档)、修复编码问题 |
| v1.2 | 2026-05-21 | 新增PDF转Markdown功能、扩展templates知识库(包含招投标知识文档)、更新模板知识读取逻辑 |
| v1.1 | 2026-05-21 | 新增Markdown转换功能、.doc支持、编码兼容性改进、环境检查工具 |
| v1.0 | 2026-05-21 | 初始版本,整合标书生成功能 |
Q: 扫描版PDF无法解析怎么办? A: 使用OCR工具(如ABBYY FineReader、Adobe Acrobat)先进行文字识别,然后重新提交。
Q: 生成的标书字数不达标怎么办? A: 系统会自动检查字数,如果不达标会提示需要补充的内容章节。
Q: 如何修改格式标准?
A: 可以通过 --format-standard 参数选择不同的格式标准,或修改 scripts/format_docx.py 中的 FORMAT_STANDARDS 配置自定义格式。
Q: 占位符如何批量替换? A: 使用Word的查找替换功能(Ctrl+H),搜索占位符类型进行批量定位。
templates/00_标书制作指南.md - 标书制作完整指南templates/bid_doc_*.md - 标书知识文档templates/bid_knowledge_*.md - 招投标知识文档© Get00, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 54 other files (scripts, references) in BiaoShu-writer-pro of Get00/BiaoShu-SKILL.
Open the folder on GitHubat commit 23ec3ae
Industry Bid Document Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Industry Bid Document Writer this skillGet00/BiaoShu-SKILL | 172 | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Word Document Reader and WriterHKUDS/DeepTutor | 41k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| BiSheng DOCX Builderdataelement/bisheng | 12k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| DOCX ToolkitXiaomiMiMo/MiMo-Code | 14k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Markdown to Word Convertercat-xierluo/SuitAgent | 205 | — | ~559 | Automated safety check: Pass | MIT | |
| Office File Processxstongxue/best-skills | 3k | — | ~1.8k | Automated safety check: Pass | Proprietary |
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
dataelement/bisheng
Builds or edits Word .docx documents inside BiSheng's code executor with python-docx, handling Chinese fonts, tables of contents, page numbers and official-document layout.
XiaomiMiMo/MiMo-Code
Produces, edits and reads Microsoft Word files through python-docx and lxml, with a decision table for picking the lightest workflow for a given task.
cat-xierluo/SuitAgent
Converts Markdown files into Word documents formatted to Chinese typesetting conventions, with presets for academic, legal, report and book layouts.
xstongxue/best-skills
处理 Office 文档的一站式 skill:Word(.doc/.docx/.dotx)、Excel(.xls/.xlsx/.xlsm/.csv)、PowerPoint(.ppt/.pptx/.potx) 的创建、读取、编辑、提取、转换、校验。触发:『读取 word 文档』『提取 excel 内容』『看 ppt 讲了什么』、.doc 老格式打不开、生成/编辑 Word…
ferdinandobons/brand-docs
Brand-aware Word engine. An agent skill from ferdinandobons/brand-docs.
Works with
Categories
Converts a tender document into Markdown, extracts scoring criteria and requirements, then drafts an industry-formatted technical bid as a Word file. Written in Chinese, this skill automates the technical part of a bid document. You send a tender file in PDF, DOCX, DOC, TXT or XLSX form, and the tool converts it to Markdown, detects which industry it belongs to, extracts scoring items, weights and key qualification, technical and commercial requirements, and pulls out the project name.
Industry Bid Document Writer fits situations like: drafting the technical bid for a tender document; extracting scoring criteria and mandatory requirements from a tender file; producing a bid outline from the scoring standard; formatting a bid as a Word file to government or enterprise conventions.
Run `npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a claude-code`. Or copy the skill folder (BiaoShu-writer-pro in Get00/BiaoShu-SKILL) into .claude/skills/bid-writer-pro in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a codex`. Or copy the skill folder (BiaoShu-writer-pro in Get00/BiaoShu-SKILL) into .agents/skills/bid-writer-pro in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Get00/BiaoShu-SKILL --skill bid-writer-pro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bid-writer-pro, .gemini/skills/bid-writer-pro, .github/skills/bid-writer-pro and .opencode/skills/bid-writer-pro in your project.
Going by SKILL.md and its folder, Industry Bid Document Writer needs Python for the scripts in its folder and the command-line tools its instructions call (python and pip). Our summary lists: Python with python-docx, pdfplumber, openpyxl, PyPDF2, jieba, pandas and pywin32; Chinese fonts such as SimSun and SimHei installed.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Industry Bid Document Writer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Industry Bid Document Writer: Word Document Reader and Writer (HKUDS/DeepTutor, 41k stars), BiSheng DOCX Builder (dataelement/bisheng, 12k stars), DOCX Toolkit (XiaomiMiMo/MiMo-Code, 14k stars) and Markdown to Word Converter (cat-xierluo/SuitAgent, 205 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Get00 (a GitHub user) maintains it in Get00/BiaoShu-SKILL, which has 172 GitHub stars. The repository was last updated on September 24, 2026.
Source: Get00/BiaoShu-SKILL on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.