lanyuanxiaoyao/Skill
1
0
Fork 0
Code Activity

优化路径

Browse Source
This commit is contained in:
兰缘小妖
2026-02-25 18:28:45 +08:00
parent 1362972630
commit d296f97a71
6 changed files with 29 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
skills/lyxy-reader-office/SKILL.md
View File

@@ -55,10 +55,10 @@ compatibility: Requires Python 3.6+. DOCX/PPTX/XLSX 无需额外依赖（XML 原
```bash
# 使用 lyxy-runner-python（推荐）
uv run --with "markitdown[docx]" skills/lyxy-reader-office/scripts/parser.py /path/to/file.docx
uv run --with "markitdown[docx]" scripts/parser.py /path/to/file.docx
# 降级到直接执行
python3 skills/lyxy-reader-office/scripts/parser.py /path/to/file.docx
python3 scripts/parser.py /path/to/file.docx
```
## References

20
skills/lyxy-reader-office/references/examples.md
View File

@@ -4,46 +4,46 @@
```bash
# DOCX
uv run --with "markitdown[docx]" skills/lyxy-reader-office/scripts/parser.py /path/to/report.docx
uv run --with "markitdown[docx]" scripts/parser.py /path/to/report.docx
# PPTX
uv run --with "markitdown[pptx]" skills/lyxy-reader-office/scripts/parser.py /path/to/slides.pptx
uv run --with "markitdown[pptx]" scripts/parser.py /path/to/slides.pptx
# XLSX
uv run --with "markitdown[xlsx]" skills/lyxy-reader-office/scripts/parser.py /path/to/data.xlsx
uv run --with "markitdown[xlsx]" scripts/parser.py /path/to/data.xlsx
# PDF
uv run --with "markitdown[pdf]" --with pypdf skills/lyxy-reader-office/scripts/parser.py /path/to/doc.pdf
uv run --with "markitdown[pdf]" --with pypdf scripts/parser.py /path/to/doc.pdf
```
## 获取文档字数
```bash
uv run --with "markitdown[docx]" skills/lyxy-reader-office/scripts/parser.py -c /path/to/report.docx
uv run --with "markitdown[docx]" scripts/parser.py -c /path/to/report.docx
```
## 提取所有标题
```bash
uv run --with "markitdown[docx]" skills/lyxy-reader-office/scripts/parser.py -t /path/to/report.docx
uv run --with "markitdown[docx]" scripts/parser.py -t /path/to/report.docx
```
## 提取指定章节
```bash
uv run --with "markitdown[docx]" skills/lyxy-reader-office/scripts/parser.py -tc "第一章" /path/to/report.docx
uv run --with "markitdown[docx]" scripts/parser.py -tc "第一章" /path/to/report.docx
```
## 搜索关键词
```bash
uv run --with "markitdown[docx]" skills/lyxy-reader-office/scripts/parser.py -s "关键词" -n 3 /path/to/report.docx
uv run --with "markitdown[docx]" scripts/parser.py -s "关键词" -n 3 /path/to/report.docx
```
## PDF OCR 高精度解析
```bash
uv run --with docling --with pypdf skills/lyxy-reader-office/scripts/parser.py /path/to/scanned.pdf --high-res
uv run --with docling --with pypdf scripts/parser.py /path/to/scanned.pdf --high-res
```
## 降级到直接 Python 执行
@@ -51,5 +51,5 @@ uv run --with docling --with pypdf skills/lyxy-reader-office/scripts/parser.py /
仅当 lyxy-runner-python skill 不存在时使用：
```bash
python3 skills/lyxy-reader-office/scripts/parser.py /path/to/file.docx
python3 scripts/parser.py /path/to/file.docx
```

22
skills/lyxy-reader-office/references/parsers.md
View File

@@ -11,23 +11,23 @@
### 使用 uv（推荐）
```bash
# DOCX - 推荐依赖
uv run --with "markitdown[docx]" skills/lyxy-reader-office/scripts/parser.py /path/to/file.docx
# DOCX - 全依赖
uv run --with docling --with "unstructured[docx]" --with markdownify --with pypandoc-binary --with "markitdown[docx]" --with python-docx scripts/parser.py /path/to/file.docx
# PPTX - 推荐依赖
uv run --with "markitdown[pptx]" skills/lyxy-reader-office/scripts/parser.py /path/to/file.pptx
# PPTX - 全依赖
uv run --with docling --with "unstructured[pptx]" --with markdownify --with "markitdown[pptx]" --with python-pptx scripts/parser.py /path/to/file.pptx
# XLSX - 推荐依赖
uv run --with "markitdown[xlsx]" skills/lyxy-reader-office/scripts/parser.py /path/to/file.xlsx
# XLSX - 全依赖
uv run --with docling --with "unstructured[xlsx]" --with markdownify --with "markitdown[xlsx]" --with pandas --with tabulate scripts/parser.py /path/to/file.xlsx
# PDF - 推荐依赖
uv run --with "markitdown[pdf]" --with pypdf skills/lyxy-reader-office/scripts/parser.py /path/to/file.pdf
# PDF - 全依赖（基础文本提取）
uv run --with docling --with "unstructured[pdf]" --with markdownify --with "markitdown[pdf]" --with pypdf scripts/parser.py /path/to/file.pdf
# PDF OCR 高精度模式
uv run --with docling --with pypdf skills/lyxy-reader-office/scripts/parser.py /path/to/file.pdf --high-res
# PDF OCR 高精度模式（全依赖）
uv run --with docling --with "unstructured[pdf]" --with unstructured-paddleocr --with "paddlepaddle==2.6.2" --with ml-dtypes --with markdownify --with "markitdown[pdf]" --with pypdf scripts/parser.py /path/to/file.pdf --high-res
```
> **注意**：以上为最小推荐依赖，更多解析器依赖和完整安装命令请查阅 `scripts/README.md` 的安装部分。
> **说明**：以上为全依赖安装命令，包含所有解析器以获得最佳兼容性。详细的解析器优先级和对比请查阅 `scripts/README.md`。
## 各格式输出特点

2
skills/lyxy-runner-js/SKILL.md
View File

@@ -54,7 +54,7 @@ Bun 特性：
```bash
# 生成临时文件路径
TEMP_FILE=$(bun skills/lyxy-runner-js/scripts/get_temp_path.js js)
TEMP_FILE=$(bun scripts/get_temp_path.js js)
# 写入脚本内容
cat <<EOF > "$TEMP_FILE"

6
skills/lyxy-runner-js/references/best-practices.md
View File

@@ -55,7 +55,7 @@ process.exit(0) // 成功
**CLI 使用方式:**
```bash
bun skills/lyxy-runner-js/scripts/get_temp_path.js <extension>
bun scripts/get_temp_path.js <extension>
```
**参数:**
@@ -75,9 +75,9 @@ bun skills/lyxy-runner-js/scripts/get_temp_path.js <extension>
**示例:**
```bash
$ bun skills/lyxy-runner-js/scripts/get_temp_path.js js
$ bun scripts/get_temp_path.js js
/var/folders/8m/0hm18pdd7ts2bwp0530drz500000gn/T/lyxy-runner-js-1770257905333-na6ujx.js
$ bun skills/lyxy-runner-js/scripts/get_temp_path.js ts
$ bun scripts/get_temp_path.js ts
/var/folders/8m/0hm18pdd7ts2bwp0530drz500000gn/T/lyxy-runner-js-1770257905333-v8yzt.ts
```

4
skills/lyxy-runner-js/references/examples.md
View File

@@ -48,7 +48,7 @@ bun ./scripts/new-script.js
bun --version
# 步骤 2: 生成临时文件路径
TEMP_FILE=$(bun skills/lyxy-runner-js/scripts/get_temp_path.js js)
TEMP_FILE=$(bun scripts/get_temp_path.js js)
# 步骤 3: 将脚本内容写入临时文件
cat <<EOF > "$TEMP_FILE"
@@ -67,7 +67,7 @@ bun "$TEMP_FILE"
```bash
# 生成 TypeScript 临时文件
TEMP_TS=$(bun skills/lyxy-runner-js/scripts/get_temp_path.js ts)
TEMP_TS=$(bun scripts/get_temp_path.js ts)
# 写入 TypeScript 脚本
cat <<EOF > "$TEMP_TS"