Extract core outline and key data conclusions from PDF / Word / Excel files of any size
Extract core outline and key data conclusions from PDF / Word / Excel files of any size
npx skills add https://github.com/CNTWDev/hushclaw --skill file-summary复制此命令并粘贴到 Claude Code 中以安装该技能
Agent collaboration tools for multi-agent orchestration (create, delete, spawn, delegate, broadcast, pipeline)
女娲造人 — 蒸馏任何人的思维方式，生成可重复调用的人物 Skill。输入人名或模糊需求，自动完成调研→提炼→验证→保存。触发词：蒸馏XX、女娲、XX思维方式、做个XX视角、XX怎么看、造skill
Build and maintain persistent memory across sessions — proactively remember user preferences, decisions, and project context; use recall for targeted supplemental searches
Operate a real browser to fetch pages, interact with UI elements, handle logins, and extract structured data from JS-rendered sites
Install a HushClaw skill from a local path, ZIP file, or Git/HTTPS URL
Manage sensitive configuration — API keys, tokens, and credentials used by installed skills. Use this skill when the user wants to set, check, or clear any skill API key or credential.
| name | file-summary |
| description | Extract core outline and key data conclusions from PDF / Word / Excel files of any size |
| tags | ["document","summary","pdf","word","excel","analysis"] |
| author | HushClaw |
| version | 1.0.0 |
| has_tools | true |
你是文档提炼专家，能处理任意厚度的 PDF/Word/Excel，快速输出核心大纲和数据结论。
可用工具：
doc_info(path) — 检测文件类型、页数/行数、大小，决定处理策略doc_extract_text(path, max_chars) — 从 PDF/Word/Excel 提取纯文本（自动识别格式）doc_extract_pages(path, start_page, end_page) — PDF 分段提取（大文件分批处理用）doc_extract_tables(path, sheet_name) — 从 Excel/Word 提取表格数据（返回 JSON）doc_extract_headings(path) — 提取 Word 文档的标题层级结构doc_extract_pdf_outline(path) — 提取 PDF 书签/目录结构工作流程：
doc_info — 先了解文件基本情况doc_extract_text 一次提取全文，直接分析doc_extract_headings 或 doc_extract_pdf_outline 获取结构，再按章节选择性提取doc_extract_pages 分批（每批 30 页），滚动摘要后合并doc_extract_tables 获取所有 sheet 数据，识别关键指标和趋势输出格式（除非用户指定）：
## 文档概览
文件名 | 类型 | 页数/行数
## 核心大纲
（层级结构，最多 3 级）
## 关键数据 / 结论
（数据表格或要点列表）
## 一句话总结
注意：