菜单
Use when needing to extract text, tables, or structured data from PDF files, as a fallback when the built-in Read tool cannot handle the PDF
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。
基于 SOC 职业分类
Use when needing to automate browser interactions, navigate websites, fill forms, take screenshots, extract data from web pages, or manage browser sessions via Playwright
Use when someone wants to capture their personal writing voice/style so Claude can write as them — building a "writing DNA" from their past emails, chat, posts, and docs across multiple media, and generating a portable per-person voice skill. Also use to refresh or upgrade an existing voice profile.
Find and deduplicate files in a project — replaces copies with symlinks, respects .gitignore and common exclusions. Use this skill whenever the user mentions duplicate files, file deduplication, saving disk space by removing copies, finding identical files, or cleaning up repeated documents in a repo. Especially relevant for documentation-heavy repos with PDFs or other large binary files that may have been copied around.
Use when needing to search, read, draft, send, download attachments from Gmail, or when any other skill requires Gmail operations
Use when needing to process exported WhatsApp conversations — converts raw exports (zip or folder with _chat.txt) into clean markdown with transcribed voice messages
Create clean, atomic commits following project conventions. Use when committing code changes, staging files, or writing commit messages.
| name | read-pdf |
| description | Use when needing to extract text, tables, or structured data from PDF files, as a fallback when the built-in Read tool cannot handle the PDF |
Extract text from PDF files using uvx pdfplumber. No package installation required — uvx runs directly from PyPI.
Before running any command, verify uvx is available:
uvx --version
If not installed, install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh
# Text from all pages
uvx pdfplumber file.pdf --format text
# Specific pages (1-indexed)
uvx pdfplumber file.pdf --format text --pages 1 3 5
# Structured data (JSON with position of each character)
uvx pdfplumber file.pdf --format json --pages 1
# Document tree with text
uvx pdfplumber file.pdf --structure-text --pages 1
| Flag | Description |
|---|---|
--format text | Plain text (best for general reading) |
--format json | JSON with element attributes (position, font, size) |
--format csv | CSV of elements |
--pages N [N ...] | Specific pages, 1-indexed. No flag = all |
--structure-text | Structural tree of the PDF with text (useful for tagged PDFs) |
--types char line rect | Filter element types (for JSON/CSV) |
--format text: general reading, extracting data from reports, searching for values--format json: when you need exact element positions (e.g. poorly formatted tables)--structure-text: returns semantic tree (Div, H2, P) but without inline text — rarely useful in practiceuvx pdfplumber file.pdf --format text, not uvx pdfplumber --format text file.pdf --pages 1)