← 返回 Skills 市场
232
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install pdf-all-in-one
功能描述
All-in-one PDF processing tool. Merge, split, extract, convert PDFs. Supports text extraction, table recognition, PDF-to-image conversion, OCR. Triggers: PDF...
安全使用建议
This skill's code and docs are consistent with a PDF processing tool and do not attempt network exfiltration or require secrets — that is a good sign. Before using it: 1) Verify the skill's source/author (homepage is missing and LICENSE claims Anthropic while the registry owner differs) — if provenance matters, treat this as untrusted until you confirm origin. 2) Install and run in an isolated environment (container or disposable VM) because the scripts will execute locally and may require sudo to install system tools (poppler, ImageMagick, tesseract, qpdf/pdftk). 3) Review the bundled scripts (they are included) yourself; pay attention to the monkeypatch in fill_fillable_fields.py (it patches a pypdf internal method — unusual but local). 4) Only run the scripts on non-sensitive PDFs or copies until you’re comfortable with behavior and output. If you need higher assurance, ask the publisher for a canonical homepage/repository or a signed release.
功能分析
Type: OpenClaw Skill
Name: pdf-all-in-one
Version: 1.0.2
The pdf-all-in-one skill bundle is a comprehensive and well-documented toolset for PDF manipulation, including merging, splitting, OCR, and form filling. The included Python scripts (e.g., extract_form_field_info.py, fill_fillable_fields.py) use standard libraries like pypdf and pdfplumber to perform legitimate document processing tasks. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions in SKILL.md and forms.md are strictly focused on guiding the AI agent through complex PDF workflows.
能力评估
Purpose & Capability
The name/description (PDF processing, merge/split/convert/ocr/fill) matches the included Python scripts and docs: extract_form_structure, converters, form-fillers, bounding-box checks, etc. The reference docs list a broad set of libraries (pypdf, pdfplumber, pdf2image, pytesseract, pypdfium2, reportlab) which are appropriate for the stated purpose. However, the registry metadata declares no required binaries or system dependencies even though SKILL.md and scripts instruct the user to install system tools (poppler/pdftoppm/pdftotext, ImageMagick 'magick', qpdf/pdftk, tesseract) — that mismatch is an engineering/provenance inconsistency worth noting.
Instruction Scope
SKILL.md and the scripts operate on local PDF files and local output directories (workspace: <current_workspace>/pdf-all-in-one-workspace/). The instructions reference only local file operations, CLI tools, and Python libraries. The runtime instructions do not direct data to external network endpoints or request unrelated system files or credentials. They do instruct installing and using system utilities (poppler, ImageMagick) and editing/creating PDFs and images — expected for this functionality.
Install Mechanism
There is no install spec (instruction-only), which is low-risk from an automatic install perspective. The package does include multiple Python scripts bundled with the skill; running them requires installing third-party Python packages and system utilities manually. The instructions point to installing via pip and OS package managers (apt/yum/brew) and using ImageMagick; those are common but not declared in registry metadata.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The scripts do not read environment variables or network credentials. They operate solely on user-supplied PDF files and JSON form descriptions, so there is no disproportionate secret access requested.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system-wide privileges. It is user-invocable and allows normal autonomous invocation (platform default). The scripts write output files into the declared workspace and do not modify other skills or global agent configuration.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install pdf-all-in-one - 安装完成后，直接呼叫该 Skill 的名称或使用
/pdf-all-in-one触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
Added PDF to image conversion feature, renamed from pdf-cn
元数据
常见问题
PDF All-in-One 是什么？
All-in-one PDF processing tool. Merge, split, extract, convert PDFs. Supports text extraction, table recognition, PDF-to-image conversion, OCR. Triggers: PDF... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 232 次。
如何安装 PDF All-in-One？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pdf-all-in-one」即可一键安装，无需额外配置。
PDF All-in-One 是免费的吗？
是的，PDF All-in-One 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
PDF All-in-One 支持哪些平台？
PDF All-in-One 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 PDF All-in-One？
由 wurang（@sonicrang）开发并维护，当前版本 v1.0.2。
推荐 Skills