菜单
Command-line utility for common PDF operations: merge all PDFs in a directory into one file (with optional PPTX conversion and title pages), and extract specific pages from a PDF into a new file. Use when the user needs to combine, split, or reorganize PDF documents.
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
| name | pdf-tool |
| description | Command-line utility for common PDF operations: merge all PDFs in a directory into one file (with optional PPTX conversion and title pages), and extract specific pages from a PDF into a new file. Use when the user needs to combine, split, or reorganize PDF documents. |
| version | 1.0.0 |
| author | Zijian Guo |
| license | MIT |
| platforms | ["linux","macos"] |
| prerequisites | {"commands":["python3","uv"]} |
| metadata | {"hermes":{"tags":["pdf","documents","merge","extract","convert","pptx","office"]}} |
Merge and extract PDF files from the command line using a single Python script.
uv pip install pypdf reportlab
For PPTX conversion, LibreOffice must also be installed:
brew install --cask libreofficeapt install libreoffice or dnf install libreofficeAfter installing this skill, the helper script is at:
~/.hermes/skills/pdf-tool/scripts/pdf_tool.py
Set a short alias for convenience:
PDF="~/.hermes/skills/pdf-tool/scripts/pdf_tool.py"
| Action | Command |
|---|---|
| Merge all PDFs in current directory | python3 $PDF merge |
| Merge PDFs in a specific directory | python3 $PDF merge -d ./slides -o output.pdf |
| Merge with PPTX files included | python3 $PDF merge -d ./slides --include-pptx |
| Merge with title pages | python3 $PDF merge -d ./slides --prepend-titles |
| Extract pages 1, 3, and 5–8 | python3 $PDF extract report.pdf -p 1,3,5-8 |
| Extract page 2 to a specific path | python3 $PDF extract report.pdf -p 2 -o page2.pdf |
merge with -d and -o. Add --include-pptx if PPTX files should be included, --prepend-titles for title pages.extract with the input path, -p for pages, and -o for output.merge| Option | Default | Description |
|---|---|---|
-d, --directory | . | Directory to scan for PDF files (non-recursive) |
-o, --output | merged.pdf | Output file path |
--include-pptx | — | Also convert and include PPTX files (requires LibreOffice) |
--prepend-titles | — | Insert a title page with the source filename before each document |
--soffice-path | — | Explicit path to the LibreOffice soffice binary |
extract| Option | Default | Description |
|---|---|---|
input | (required) | Path to the source PDF |
-p, --pages | (required) | Page selection: comma-separated numbers and ranges, e.g. 1,3-5,8 |
-o, --output | extracted.pdf | Output file path (placed next to source file if relative) |
--soffice-path explicitly.1 is the first page, not 0.start must be less than or equal to end in a range spec (e.g. 5-3 is invalid).Build and run lightweight regression evaluations for agents, tools, prompts, and workflows. Use when comparing agent versions, catching behavior drift, measuring pass rates over repeated runs, or turning production failures into replayable test cases.
Audit agent repositories, MCP configurations, tool schemas, prompts, and logs for common security risks: secret exposure, prompt injection payloads, tool poisoning, command execution, broad filesystem access, and unsafe auto-approval.
Inspect agent traces, tool-call logs, and OpenTelemetry/OpenInference-style span exports. Use when debugging why an agent skipped a tool, called the wrong tool, hit errors, exceeded latency budgets, or produced an unsupported answer.
Design and validate graph/state-machine agent workflows with explicit starts, terminal states, guarded cycles, human approval points, and side-effecting tool boundaries. Use when building LangGraph-style, multi-agent, or durable agent workflows.
Safely list, create, and extract zip/tar archives with path traversal checks. Use when packaging artifacts, unpacking downloaded files, or inspecting archive contents on a user's computer.
Build, run, and review browser-using AI agents with Playwright, Browser Use, MCP browser tools, or hosted browser runtimes. Use for web navigation agents, form-filling, UI task automation, screenshots, DOM/vision checks, auth/session handling, and browser-task reliability reviews.