@panda-agent/panda-cli 0.1.29 → 0.1.31

package/bundled-preset-skills/pdf/.skill-metadata.yaml

@@ -0,0 +1,273 @@
+examples:
+  - id: extract-text
+    title:
+      zh: 提取文本内容
+      en: Extract Text Content
+    description:
+      zh: 从 PDF 文件中准确提取文本和结构化信息
+      en: Accurately extract text and structured information from PDF files
+    prompt:
+      zh: |-
+        请帮我从这个 PDF 文件中提取内容：
+
+        文件路径：{{PDF文件路径}}
+
+        提取要求：
+        1. 完整文本提取：
+           - 保留原文本顺序和段落结构
+           - 处理多栏布局的文本流
+           - 识别和提取标题层级
+        2. 结构化信息：
+           - 目录/索引信息
+           - 页眉页脚内容
+           - 页码和章节信息
+        3. 特殊内容：
+           - 表格数据的结构化提取
+           - 图片的描述性文字
+           - 链接和引用信息
+        4. 输出格式：
+           - 纯文本版本
+           - 结构化的 JSON 格式
+           - Markdown 格式（保持层次结构）
+
+        请提供多种格式的提取结果。
+      en: |-
+        Please help me extract content from this PDF file:
+
+        File path: {{PDF file path}}
+
+        Extraction requirements:
+        1. Complete text extraction:
+           - Preserve original text order and paragraph structure
+           - Handle text flow in multi-column layouts
+           - Identify and extract heading hierarchies
+        2. Structured information:
+           - Table of contents/index information
+           - Header and footer content
+           - Page numbers and chapter information
+        3. Special content:
+           - Structured extraction of table data
+           - Descriptive text for images
+           - Link and citation information
+        4. Output formats:
+           - Plain text version
+           - Structured JSON format
+           - Markdown format (preserving hierarchy)
+
+        Please provide extraction results in multiple formats.
+  - id: merge-split
+    title:
+      zh: 合并分割PDF
+      en: Merge and Split PDF
+    description:
+      zh: 合并多个PDF文件或将PDF分割成多个部分
+      en: Merge multiple PDF files or split PDF into multiple parts
+    prompt:
+      zh: |-
+        我需要处理这些 PDF 文件：
+
+        操作类型：{{合并/分割}}
+
+        如果是合并：
+        文件列表：
+        1. {{第一个PDF文件路径}}
+        2. {{第二个PDF文件路径}}
+        3. {{第三个PDF文件路径}}
+
+        合并要求：
+        - 按指定顺序合并
+        - 保持原有页面质量和格式
+        - 添加书签结构（可选）
+        - 生成目录页（可选）
+
+        如果是分割：
+        源文件：{{源PDF文件路径}}
+        分割方式：
+        - 按页码范围分割：{{起始页}}-{{结束页}}
+        - 按章节自动分割
+        - 按书签结构分割
+        - 每N页分割一次
+
+        输出要求：
+        - 保持原始质量
+        - 文件命名规范
+        - 添加页码信息
+
+        请执行相应操作并提供处理后的文件。
+      en: |-
+        I need to process these PDF files:
+
+        Operation type: {{Merge/Split}}
+
+        If merging:
+        File list:
+        1. {{First PDF file path}}
+        2. {{Second PDF file path}}
+        3. {{Third PDF file path}}
+
+        Merge requirements:
+        - Merge in specified order
+        - Maintain original page quality and formatting
+        - Add bookmark structure (optional)
+        - Generate table of contents page (optional)
+
+        If splitting:
+        Source file: {{Source PDF file path}}
+        Split method:
+        - Split by page range: {{Start page}}-{{End page}}
+        - Split by chapters automatically
+        - Split by bookmark structure
+        - Split every N pages
+
+        Output requirements:
+        - Maintain original quality
+        - Standardized file naming
+        - Add page number information
+
+        Please execute the corresponding operation and provide the processed files.
+  - id: form-processing
+    title:
+      zh: 表单处理
+      en: Form Processing
+    description:
+      zh: 处理PDF表单：填写、提取数据、验证等
+      en: "Process PDF forms: filling, data extraction, validation, etc."
+    prompt:
+      zh: |-
+        请帮我处理这个 PDF 表单文件：
+
+        表单文件：{{PDF表单文件路径}}
+
+        操作类型：{{填写表单/提取数据/验证表单}}
+
+        如果是填写表单：
+        数据来源：{{JSON数据或键值对}}
+        字段映射：
+        - 姓名 -> {{name_field}}
+        - 日期 -> {{date_field}}
+        - 金额 -> {{amount_field}}
+        - 选择项 -> {{choice_field}}
+
+        填写要求：
+        - 准确填入所有必填字段
+        - 保持原有表单格式
+        - 添加数字签名（如果需要）
+        - 验证数据有效性
+
+        如果是提取数据：
+        - 提取所有已填写的字段值
+        - 识别表单结构和字段类型
+        - 验证数据完整性
+        - 输出结构化数据
+
+        如果是验证表单：
+        - 检查必填字段是否完整
+        - 验证数据格式是否正确
+        - 检查逻辑关系
+        - 生成验证报告
+
+        请根据指定操作类型执行相应处理。
+      en: |-
+        Please help me process this PDF form file:
+
+        Form file: {{PDF form file path}}
+
+        Operation type: {{Fill form/Extract data/Validate form}}
+
+        If filling form:
+        Data source: {{JSON data or key-value pairs}}
+        Field mapping:
+        - Name -> {{name_field}}
+        - Date -> {{date_field}}
+        - Amount -> {{amount_field}}
+        - Choice -> {{choice_field}}
+
+        Filling requirements:
+        - Accurately fill all required fields
+        - Maintain original form formatting
+        - Add digital signature (if needed)
+        - Validate data validity
+
+        If extracting data:
+        - Extract all filled field values
+        - Identify form structure and field types
+        - Validate data completeness
+        - Output structured data
+
+        If validating form:
+        - Check if required fields are complete
+        - Validate data format correctness
+        - Check logical relationships
+        - Generate validation report
+
+        Please execute corresponding processing based on specified operation type.
+  - id: watermark-security
+    title:
+      zh: 水印和安全处理
+      en: Watermark and Security Processing
+    description:
+      zh: 添加水印、密码保护和权限控制
+      en: Add watermarks, password protection and permission control
+    prompt:
+      zh: |-
+        请帮我为这个 PDF 文件添加安全保护：
+
+        源文件：{{源PDF文件路径}}
+
+        安全措施：
+        1. 水印添加：
+           - 文本水印：{{公司名称}} - {{机密等级}}
+           - 图片水印：{{logo文件路径}}
+           - 水印位置：页面中心/对角线/平铺
+           - 透明度设置：{{透明度百分比}}
+        2. 密码保护：
+           - 打开密码：{{open_password}}
+           - 编辑密码：{{edit_password}}
+           - 密码强度要求
+        3. 权限控制：
+           - 禁止打印
+           - 禁止复制文本
+           - 禁止编辑内容
+           - 限制页面提取
+        4. 其他安全选项：
+           - 数字签名
+           - 文档加密算法
+           - 访问日志记录
+
+        输出要求：
+        - 保持文档原始质量
+        - 确保安全措施有效
+        - 提供安全设置说明
+
+        请实施相应的安全保护措施。
+      en: |-
+        Please help me add security protection to this PDF file:
+
+        Source file: {{Source PDF file path}}
+
+        Security measures:
+        1. Watermark addition:
+           - Text watermark: {{Company Name}} - {{Confidentiality Level}}
+           - Image watermark: {{logo file path}}
+           - Watermark position: Center/Diagonal/Tile
+           - Transparency setting: {{transparency percentage}}
+        2. Password protection:
+           - Open password: {{open_password}}
+           - Edit password: {{edit_password}}
+           - Password strength requirements
+        3. Permission control:
+           - Disable printing
+           - Disable text copying
+           - Disable content editing
+           - Restrict page extraction
+        4. Other security options:
+           - Digital signature
+           - Document encryption algorithm
+           - Access log recording
+
+        Output requirements:
+        - Maintain original document quality
+        - Ensure security measures are effective
+        - Provide security settings documentation
+
+        Please implement corresponding security protection measures.

package/bundled-preset-skills/pdf/LICENSE.txt

@@ -0,0 +1,30 @@
+© 2025 Anthropic, PBC. All rights reserved.
+
+LICENSE: Use of these materials (including all code, prompts, assets, files,
+and other components of this Skill) is governed by your agreement with
+Anthropic regarding use of Anthropic's services. If no separate agreement
+exists, use is governed by Anthropic's Consumer Terms of Service or
+Commercial Terms of Service, as applicable:
+https://www.anthropic.com/legal/consumer-terms
+https://www.anthropic.com/legal/commercial-terms
+Your applicable agreement is referred to as the "Agreement." "Services" are
+as defined in the Agreement.
+
+ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
+contrary, users may not:
+
+- Extract these materials from the Services or retain copies of these
+  materials outside the Services
+- Reproduce or copy these materials, except for temporary copies created
+  automatically during authorized use of the Services
+- Create derivative works based on these materials
+- Distribute, sublicense, or transfer these materials to any third party
+- Make, offer to sell, sell, or import any inventions embodied in these
+  materials
+- Reverse engineer, decompile, or disassemble these materials
+
+The receipt, viewing, or possession of these materials does not convey or
+imply any license or right beyond those expressly granted above.
+
+Anthropic retains all right, title, and interest in these materials,
+including all copyrights, patents, and other intellectual property rights.

package/bundled-preset-skills/pdf/SKILL.md

@@ -0,0 +1,324 @@
+---
+name: pdf
+version: 1.0.1
+description: Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
+description_zh: 当用户需要对 PDF 文件执行任何操作时使用此技能。包括：读取或提取 PDF 中的文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新 PDF、填写 PDF 表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。只要用户提及 .pdf 文件或要求生成 PDF，就使用此技能。
+license: Proprietary. LICENSE.txt has complete terms
+---
+
+# Working with PDF Documents
+
+## Introduction
+
+A comprehensive toolkit for PDF manipulation through Python and shell utilities. Consult `advanced-reference.md` for extended capabilities (pypdfium2, JavaScript ecosystems, performance guidance). When form-filling is required, follow the workflow described in `form-filling-guide.md`.
+
+## Getting Started
+
+```python
+import pypdf
+
+# Open and inspect a document
+doc = pypdf.PdfReader("document.pdf")
+total_pages = len(doc.pages)
+print("Pages: {}".format(total_pages))
+
+# Gather all textual content
+content = "".join(pg.extract_text() for pg in doc.pages)
+```
+
+## Core Python Libraries
+
+### pypdf — Structural Manipulation
+
+#### Combining Multiple Documents
+
+```python
+import pypdf
+
+output = pypdf.PdfWriter()
+sources = ["doc1.pdf", "doc2.pdf", "doc3.pdf"]
+for src in sources:
+    rdr = pypdf.PdfReader(src)
+    for pg in rdr.pages:
+        output.add_page(pg)
+
+with open("merged.pdf", "wb") as dest:
+    output.write(dest)
+```
+
+#### Separating Pages Into Individual Files
+
+```python
+import pypdf
+
+source = pypdf.PdfReader("input.pdf")
+for idx, pg in enumerate(source.pages):
+    single = pypdf.PdfWriter()
+    single.add_page(pg)
+    with open("page_{}.pdf".format(idx + 1), "wb") as dest:
+        single.write(dest)
+```
+
+#### Reading Document Properties
+
+```python
+import pypdf
+
+source = pypdf.PdfReader("document.pdf")
+props = source.metadata
+print("Title: {}".format(props.title))
+print("Author: {}".format(props.author))
+print("Subject: {}".format(props.subject))
+print("Creator: {}".format(props.creator))
+```
+
+#### Changing Page Orientation
+
+```python
+import pypdf
+
+source = pypdf.PdfReader("input.pdf")
+output = pypdf.PdfWriter()
+
+target = source.pages[0]
+target.rotate(90)  # 90-degree clockwise rotation
+output.add_page(target)
+
+with open("rotated.pdf", "wb") as dest:
+    output.write(dest)
+```
+
+### pdfplumber — Content Extraction
+
+#### Retrieving Text Preserving Layout
+
+```python
+import pdfplumber
+
+with pdfplumber.open("document.pdf") as doc:
+    for pg in doc.pages:
+        content = pg.extract_text()
+        print(content)
+```
+
+#### Pulling Tabular Data
+
+```python
+import pdfplumber
+
+with pdfplumber.open("document.pdf") as doc:
+    for pg_idx, pg in enumerate(doc.pages):
+        found_tables = pg.extract_tables()
+        for tbl_idx, tbl in enumerate(found_tables):
+            print("Table {} on page {}:".format(tbl_idx + 1, pg_idx + 1))
+            for row in tbl:
+                print(row)
+```
+
+#### Structured Table Export
+
+```python
+import pdfplumber
+import pandas as pd
+
+with pdfplumber.open("document.pdf") as doc:
+    collected = []
+    for pg in doc.pages:
+        for tbl in pg.extract_tables():
+            if tbl:
+                frame = pd.DataFrame(tbl[1:], columns=tbl[0])
+                collected.append(frame)
+
+if collected:
+    merged = pd.concat(collected, ignore_index=True)
+    merged.to_excel("extracted_tables.xlsx", index=False)
+```
+
+### reportlab — Document Generation
+
+#### Producing a Simple PDF
+
+```python
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+
+doc = canvas.Canvas("hello.pdf", pagesize=letter)
+w, h = letter
+
+doc.drawString(100, h - 100, "Hello World!")
+doc.drawString(100, h - 120, "This is a PDF created with reportlab")
+
+doc.line(100, h - 140, 400, h - 140)
+
+doc.save()
+```
+
+#### Multi-Page Document Construction
+
+```python
+from reportlab.lib.pagesizes import letter
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
+from reportlab.lib.styles import getSampleStyleSheet
+
+template = SimpleDocTemplate("report.pdf", pagesize=letter)
+styles = getSampleStyleSheet()
+elements = []
+
+elements.append(Paragraph("Report Title", styles['Title']))
+elements.append(Spacer(1, 12))
+elements.append(Paragraph("This is the body of the report. " * 20, styles['Normal']))
+elements.append(PageBreak())
+
+elements.append(Paragraph("Page 2", styles['Heading1']))
+elements.append(Paragraph("Content for page 2", styles['Normal']))
+
+template.build(elements)
+```
+
+#### Handling Sub/Superscripts
+
+**IMPORTANT**: Never use Unicode subscript/superscript characters (₀₁₂₃₄₅₆₇₈₉, ⁰¹²³⁴⁵⁶⁷⁸⁹) in ReportLab PDFs. The built-in fonts do not include these glyphs, causing them to render as solid black boxes.
+
+Instead, use ReportLab's XML markup tags in Paragraph objects:
+```python
+from reportlab.platypus import Paragraph
+from reportlab.lib.styles import getSampleStyleSheet
+
+styles = getSampleStyleSheet()
+
+# Subscripts: use <sub> tag
+chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])
+
+# Superscripts: use <super> tag
+squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])
+```
+
+For canvas-drawn text (not Paragraph objects), manually adjust font the size and position rather than using Unicode subscripts/superscripts.
+
+## Shell Utilities
+
+### poppler-utils (pdftotext)
+
+```bash
+# Plain text extraction
+pdftotext input.pdf output.txt
+
+# Layout-preserving extraction
+pdftotext -layout input.pdf output.txt
+
+# Page range selection
+pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1-5
+```
+
+### qpdf
+
+```bash
+# Combine documents
+qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf
+
+# Extract page subsets
+qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
+qpdf input.pdf --pages . 6-10 -- pages6-10.pdf
+
+# Orientation adjustment
+qpdf input.pdf output.pdf --rotate=+90:1  # Rotate page 1 by 90 degrees
+
+# Decrypt protected files
+qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf
+```
+
+### pdftk (if available)
+
+```bash
+# Combine
+pdftk file1.pdf file2.pdf cat output merged.pdf
+
+# Burst into pages
+pdftk input.pdf burst
+
+# Orientation change
+pdftk input.pdf rotate 1east output rotated.pdf
+```
+
+## Typical Workflows
+
+### OCR for Scanned Documents
+
+```python
+import pytesseract
+from pdf2image import convert_from_path
+
+rendered = convert_from_path('scanned.pdf')
+
+content = ""
+for idx, frame in enumerate(rendered):
+    content += "Page {}:\n".format(idx + 1)
+    content += pytesseract.image_to_string(frame)
+    content += "\n\n"
+
+print(content)
+```
+
+### Overlaying a Watermark
+
+```python
+import pypdf
+
+stamp = pypdf.PdfReader("watermark.pdf").pages[0]
+
+source = pypdf.PdfReader("document.pdf")
+output = pypdf.PdfWriter()
+
+for pg in source.pages:
+    pg.merge_page(stamp)
+    output.add_page(pg)
+
+with open("watermarked.pdf", "wb") as dest:
+    output.write(dest)
+```
+
+### Extracting Embedded Graphics
+
+```bash
+# Using pdfimages (poppler-utils)
+pdfimages -j input.pdf output_prefix
+
+# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc.
+```
+
+### Applying Password Protection
+
+```python
+import pypdf
+
+source = pypdf.PdfReader("input.pdf")
+output = pypdf.PdfWriter()
+
+for pg in source.pages:
+    output.add_page(pg)
+
+output.encrypt("userpassword", "ownerpassword")
+
+with open("encrypted.pdf", "wb") as dest:
+    output.write(dest)
+```
+
+## Capability Matrix
+
+| Operation | Recommended Tool | Approach |
+|-----------|-----------------|----------|
+| Combine documents | pypdf | `writer.add_page(page)` |
+| Separate pages | pypdf | One file per page |
+| Read text content | pdfplumber | `page.extract_text()` |
+| Parse tables | pdfplumber | `page.extract_tables()` |
+| Generate new PDFs | reportlab | Canvas or Platypus |
+| CLI merging | qpdf | `qpdf --empty --pages ...` |
+| Scanned document OCR | pytesseract | Render to image first |
+| Form completion | pdf-lib or pypdf (see form-filling-guide.md) | See form-filling-guide.md |
+
+## Additional Resources
+
+- Extended pypdfium2 documentation: `advanced-reference.md`
+- JavaScript library details (pdf-lib): `advanced-reference.md`
+- Form-filling procedures: `form-filling-guide.md`
+- Error resolution guidance: `advanced-reference.md`