← 返回 Skills 市场
446
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install document-qa
功能描述
Answers questions based on the content of uploaded documents (PDF, DOCX, TXT), supporting individual files or entire folders.
使用说明 (SKILL.md)
Document Q&A Skill
This skill allows you to upload documents (PDF, DOCX, TXT) and ask questions about their content.
How to Use
To use this skill, run the run_qa.py script with the path to your document or folder and your question. The skill will extract text from supported files (PDF, DOCX, TXT) and provide it as context for answering your question.
Command:
python ~/.openclaw/workspace/skills/document-qa/scripts/run_qa.py "\x3Cpath_to_file_or_folder>" "\x3CYour question>"
Examples:
- To ask about a single PDF file:
python ~/.openclaw/workspace/skills/document-qa/scripts/run_qa.py "C:\Users\anandraj\.openclaw\workspace\my_docs\report.pdf" "What are the key findings?" - To ask about documents in a folder:
python ~/.openclaw/workspace/skills/document-qa/scripts/run_qa.py "C:\Users\anandraj\.openclaw\workspace\project_docs" "Summarize the project goals."
The system will extract all relevant text and present it along with your question, allowing me to formulate an answer based on the provided content.
Supported Document Types
- PDF (.pdf) (Requires 'iyeque-pdf-reader-1.1.0' skill installed)
- Microsoft Word (.docx)
- Plain Text (.txt)
- Microsoft Excel (.xlsx)
Note:
- For PDF support, ensure the
iyeque-pdf-reader-1.1.0skill is installed in your workspace. - For Excel support, you might need to install the
pandasandopenpyxllibraries if they are not already installed in your environment:pip install pandas openpyxl
安全使用建议
This skill behaves as a local document-extraction/QA helper and appears coherent, but take these precautions before installing or running it: 1) Inspect the sibling PDF reader it calls (iyeque-pdf-reader-1.1.0/reader.py) — the skill will execute that script if present, so ensure it is trusted. 2) Do not feed sensitive/private documents unless you trust the environment and the PDF reader, because the scripts print full extracted text to stdout which becomes the model context. 3) Install required Python libraries in a controlled environment (virtualenv) to avoid supply-chain risks. 4) Consider running the code in an isolated container or sandbox the first time, and review any third-party skills in your workspace for unexpected network or file-access behavior. If you can provide the contents of the PDF reader's reader.py, I can re-evaluate with higher confidence.
功能分析
Type: OpenClaw Skill
Name: document-qa
Version: 1.0.0
The OpenClaw AgentSkills bundle for 'document-qa' is classified as benign. All scripts (extract_docx.py, extract_excel.py, extract_txt.py, process_folder.py, run_qa.py) correctly implement their stated purpose of extracting text from various document types. The use of `subprocess.run` in `process_folder.py` and `run_qa.py` is secure, passing arguments as a list to `sys.executable`, which prevents shell injection vulnerabilities. The `SKILL.md` and `run_qa.py` provide clear, non-malicious instructions and context to the AI agent, aligning with the skill's function without attempting prompt injection for unauthorized actions or data exfiltration. There is no evidence of malicious intent, obfuscation, or attempts to access sensitive system resources beyond the scope of document processing.
能力评估
Purpose & Capability
Name/description (Document Q&A) align with the included scripts: extract_txt.py, extract_docx.py, extract_excel.py, process_folder.py, and run_qa.py. The PDF extraction is delegated to a named sibling skill (iyeque-pdf-reader-1.1.0), which is consistent with the SKILL.md note. Declared dependencies (pandas/openpyxl, python-docx) match the code.
Instruction Scope
SKILL.md instructs running run_qa.py which calls process_folder.py to extract text and then prints context markers and the QUESTION. The scripts operate only on the provided file/folder path. However, process_folder.py uses subprocess.run to execute a sibling PDF reader script (reader.py) if present: that delegates PDF handling to another skill and executes local code. The skill prints the full extracted text to stdout (which becomes the model's context), so sensitive content will be exposed to the agent's model input/output.
Install Mechanism
No install spec is provided (instruction-and-script-only). No downloads or package installs are automated by the skill. The only install-time concern is that users may need to pip-install expected Python libs (python-docx, pandas, openpyxl, PyPDF2) as documented.
Credentials
The skill requests no environment variables, no credentials, and no config paths. That is proportionate to its stated purpose. The code does execute local scripts via subprocess, but does not attempt to read unrelated env vars or secrets.
Persistence & Privilege
always is false and there is no self-modifying or cross-skill configuration. The skill does execute local scripts but does not request permanent presence or elevated platform privileges.
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 document-qa - 安装完成后，直接呼叫该 Skill 的名称或使用
/document-qa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
v1.0.0
- Initial release of the Document Q&A skill.
- Supports answering questions from PDF, DOCX, TXT, and XLSX files.
- Accepts both individual files and entire folders as input.
- Requires the "iyeque-pdf-reader-1.1.0" skill for PDF extraction.
- Provides simple command-line usage instructions and examples.
元数据
常见问题
All Documents QA 是什么？
Answers questions based on the content of uploaded documents (PDF, DOCX, TXT), supporting individual files or entire folders. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 446 次。
如何安装 All Documents QA？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install document-qa」即可一键安装，无需额外配置。
All Documents QA 是免费的吗？
是的，All Documents QA 完全免费（开源免费），可自由下载、安装和使用。
All Documents QA 支持哪些平台？
All Documents QA 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 All Documents QA？
由 anand2426（@anand2426）开发并维护，当前版本 v1.0.0。
推荐 Skills