Docx perfect
Word文档美化与格式化专家。专门用于将Word文档中的文本内容转换为专业表格格式，应用一致的样式（深蓝色表头、斑马纹数据行、边框），支持版本化迭代管理。当用户需要美化Word文档、创建专业表格、或递增式优化文档章节时使用此技能。From its SKILL.md
npx -y skills add aAAaqwq/AGI-Super-Team --skill docx-perfectAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.1 KB, 658 tokens by cl100k_base, as published. Nobody here has run it
DOCX文档美化专家
将Word文档中的内容转换为专业表格格式，支持版本化迭代优化。
快速开始
文档美化采用递增式版本管理（v0.1, v0.2, ..., v1.0），每次优化一个章节后生成新版本。
工作流程
1. 分析源文档
python -c "import sys; sys.stdout.reconfigure(encoding='utf-8'); from docx import Document; doc = Document('source.docx'); [print(p.text.strip()) for p in doc.paragraphs if p.text.strip()]"
2. 确定本次优化的章节
识别需要美化的章节标题，如：
3.1 实体识别→ 创建实体属性表格3.2 实体间联系→ 创建联系关系表格5.2 索引优化设计→ 创建索引汇总表格
3. 创建表格
使用 scripts/create_table.py 创建表格，参考下方脚本模板。
4. 应用样式
使用统一样式：
- 表头: 深蓝色背景 (#4472C4) + 白色粗体文字
- 数据行: 白色/浅灰色隔行变色
- 边框: 黑色单线边框
5. 版本号管理
自动递增版本号，保存为新文件：文档名-v0.X.docx
脚本模板
详见 scripts/README.md
常见表格模式
实体属性表格
| 属性名 | 类型/约束 | 说明 |
|--------|-----------|------|
| field1 | INT, PK | 主键 |
联系关系表格
| 联系 | 实体A | 实体B | 说明 |
|------|-------|-------|------|
索引汇总表格
| 表名 | 索引名 | 字段 | 类型 | 说明 |
样式规范
- 表头背景:
#4472C4(深蓝) - 表头文字: 白色、粗体、11号
- 奇数行: 白色
#FFFFFF - 偶数行: 浅灰
#E7E6E6 - 数据行文字: 宋体、10号
- 边框: 黑色单线，4磅
What ships with it: 4 files
11.3 KB alongside SKILL.md, 1 of them executable
references/
- table-patterns.md1.2 KB
- workflow.md2.2 KB
scripts/
- README.md3.9 KB
- template.pyruns4.1 KB
Gives 0 of the 12 instructions most pdf office docs skills give in 658 tokens
Counted across 569 of the 585 authors here whose files we hold, read 2026-09-06
- Ensure every slide fits inside one viewportin 20 of 569, across 11 files
- Check for product marketing context firstin 15 of 569, across 5 files
- Ask for the minimum neededin 15 of 569, across 5 files
- Set the API key environment variablein 15 of 569, across 10 files
- Support keyboard and touch navigationin 14 of 569, across 5 files
- Match the buyer stagein 13 of 569, across 3 files
- Split overflowing content into multiple slidesin 12 of 569, across 3 files
- Set page size explicitly for consistent resultsin 12 of 569, across 5 files
- Convert documents to markdown using pandocin 12 of 569, across 6 files
- Read STYLE_PRESETS.md before generatingin 12 of 569, across 7 files
- Send multipart POST requests to the APIin 12 of 569, across 7 files
- Use smart quotes for new contentin 11 of 569, across 4 files
Said here and by no other author read
- Identify chapters to optimize
- Create tables using the script
- Apply consistent table styles
- Increment version numbers
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.