菜单
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, deleting pages, creating new PDFs, and filling PDF forms. If the user mentions a .pdf file or asks to produce one, use this skill.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
skill_run 嵌入式 JavaScript 运行时能力矩阵（API、polyfill、限制）。编写或修复 skill_run 脚本前必读。
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
| name | |
| 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, deleting pages, creating new PDFs, and filling PDF forms. If the user mentions a .pdf file or asks to produce one, use this skill. |
| license | Proprietary. LICENSE.txt has complete terms |
本系统无 shell/Python 环境，外部 PDF 命令行与 Python 库一律不可用。所有操作通过内置工具完成。skill_run API 见
skill_read {"skill":"runtime"}。
| Task | Tool |
|---|---|
| 读取 PDF（推荐，所有模型） | pdf_read {"path": "doc.pdf"} — 仅 path；vision 模型 ≤4 页直接 vision，>20 页直接文本+note，5–20 页 Judge |
| 仅 PDFium 纯文本（跳过 Judge） | office_read_to_markdown {"path": "doc.pdf"} |
| 手动渲染页图（高级） | pdf_render_pages {"path": "doc.pdf"} → .cache/pdf/（pdf_read 内部会自动渲染） |
| 读取 1–4 张图片 | image_read {"paths": ["a.png","b.png"]}（vision 模型） |
| 合并 | pdf_merge {"inputs": ["a.pdf", "b.pdf"], "out_path": "merged.pdf"} |
| 拆分（按范围/逐页） | pdf_split（详见 reference.md） |
| 旋转页面 | pdf_rotate（90/180/270，详见 reference.md） |
| 删除页面 | pdf_delete_pages {"path": "in.pdf", "pages": [2, 4], "out_path": "out.pdf"} |
| 创建新 PDF | skill_run + PDFLib（见下方模板） |
| 表格数据整理 | office_read_to_markdown 提取文本 → 手工整理为 CSV → data_query |
| 填表单 | 见 forms.md（当前无自动填表工具） |
页码一律 1-based。页面工具详细参数与典型流程：skill_read {"skill": "pdf", "doc": "reference.md"}。
async function main() {
const { PDFDocument, StandardFonts, rgb } = PDFLib; // 全局 PDFLib，require('pdf-lib') 也可
const pdfDoc = await PDFDocument.create();
const page = pdfDoc.addPage([595, 842]); // A4 点数
const font = await pdfDoc.embedFont(StandardFonts.Helvetica);
page.drawText("Hello PDF", { x: 50, y: 780, size: 24, font, color: rgb(0, 0, 0) });
page.drawLine({ start: { x: 50, y: 770 }, end: { x: 545, y: 770 }, thickness: 1 });
const b64 = await pdfDoc.saveAsBase64();
doc_write("out.pdf", b64);
return { ok: true };
}
// 不要在末尾调用 main()，运行时会自动调用
pdf-lib 的 StandardFonts（Helvetica 等）不支持中文，drawText 中文会直接报编码错误，且本系统未内置中文字体文件。
中文交付物降级方案（按优先级）：
skill_run + docx 库，中文完整支持），如用户接受.ttf 中文字体文件 → fs.readFileSync(p) 读字节 → pdfDoc.embedFont(bytes)（需 fontkit，可能不可用，先小样验证）async function main() {
const { PDFDocument, degrees } = PDFLib;
const bytes = fs.readFileSync("in.pdf"); // 不带 encoding = 字节
const pdfDoc = await PDFDocument.load(bytes);
// 加水印文字 / 改 metadata / 复制页面到新文档等
pdfDoc.setTitle("New Title");
const b64 = await pdfDoc.saveAsBase64();
doc_write("out.pdf", b64);
return { pages: pdfDoc.getPageCount() };
}
简单页面操作（合并/拆分/旋转/删除）优先用原生工具（pdf_merge 等），比 pdf-lib 更快更稳。
| 操作 | 说明 |
|---|---|
| OCR / 扫描件 | 无独立 OCR 引擎；扫描件用 vision 模型 pdf_read（仅 path）；非 vision 模型会报错 |
| 加密/解密 | 加密 PDF 不支持操作；提示用户先在外部工具解密 |
| 提取内嵌图片 | 无工具 |
| 自动填 AcroForm 表单 | 见 forms.md 的降级方案 |
| 结构化表格提取 | 无自动工具；用 office_read_to_markdown 文本 + 人工整理 |
pdf_read 仅 path（含公式、扫描件、纯文本；vision 模型自动 Judge）office_read_to_markdownpdf_split / pdf_delete_pages / pdf_rotate 调整结构pdf_merge 合并交付物skill_run + PDFLib（注意中文限制）pdf_read 可走图片理解路径。