← Back to Skills Marketplace
TDOC Docx
by
WenRichard
· GitHub ↗
· v1.0.0
· MIT-0
365
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install tdoc-docx
Description
Word 文档全能处理技能 | Complete Word Document Processing Skill. 支持创建、读取、编辑、转换 Word 文档 | Create, read, edit, convert Word documents. 支持 .docx/.doc 格式、中文公文格式、表格、图片、tr...
Usage Guidance
This skill appears coherent and implements DOCX processing locally. Before installing: (1) review install.sh since it will install Python packages and system packages (may require sudo) — run it in a VM or sandbox if you want to avoid system changes; (2) inspect any helper scripts that could fetch network resources (e.g., scripts/fetch_file.sh) to confirm there are no unexpected remote downloads; (3) if you don't want the agent to call the skill autonomously, disable model invocation for this skill in agent settings; (4) no secrets or external API keys are required by the skill, so there is no obvious credential exfiltration path. If you want higher assurance, run the code in an isolated environment and audit scripts that invoke subprocesses (LibreOffice/pandoc) or perform external installs.
Capability Analysis
Type: OpenClaw Skill
Name: tdoc-docx
Version: 1.0.0
The skill bundle contains high-risk technical implementations, most notably in 'scripts/office/soffice.py', which compiles a C-based shim at runtime and uses LD_PRELOAD to intercept system socket calls (socket, accept, listen). While documented as a compatibility fix for sandboxed environments using LibreOffice, this technique is a classic malware vector for system-level manipulation. Additionally, 'scripts/fetch_file.sh' provides broad capabilities to fetch data from remote URLs and SFTP servers, which could be exploited for data exfiltration or fetching malicious payloads. Although the code uses 'defusedxml' to mitigate XXE risks, the combination of on-the-fly C compilation and arbitrary network access presents a significant security risk.
Capability Assessment
Purpose & Capability
Name/description (Word document lifecycle: create/read/edit/convert/diff/comment) aligns with the provided scripts and declared binaries. Required binaries (python3, uv) and the requested system tools (LibreOffice, pandoc, poppler, antiword) are appropriate for the stated conversion and extraction tasks.
Instruction Scope
SKILL.md and the scripts direct the agent to operate on local files (create, unpack/pack, edit XML, convert formats). Instructions do not ask for unrelated files, environment variables, or external endpoints. The skill declares an automatic trigger for document-related requests (routing rules) — this is a functional behavior rather than unexpected data access.
Install Mechanism
Install is provided (install.sh) and uses pip/uv and platform package managers (brew/apt/yum) to install Python deps and system packages (LibreOffice, pandoc, poppler, antiword). These are standard but do run network installs and may call sudo on Linux — review and run in a controlled environment if you don't want system changes.
Credentials
The skill requests no environment variables, no secrets, and no config paths. All operations appear to be local file manipulation and validation; no credentials or unrelated system configs are requested.
Persistence & Privilege
Flags: always=false, user-invocable=true, model invocation enabled (default). The skill does not request permanent/always-on inclusion or modify other skills. Autonomous invocation is allowed by default — this is normal but worth noting if you prefer to restrict autonomous tool use.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tdoc-docx - After installation, invoke the skill by name or use
/tdoc-docx - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of tdoc-docx: a complete Word document processing skill.
- Provides creation, reading, editing, conversion, and comparison for Word documents (.docx/.doc), supporting Chinese official templates, tables, images, tracked changes, and comments.
- Offers both general and specialized (industry/government) template-based document creation with a clear routing decision tree.
- Includes scripts for extracting content, batch editing, converting to/from PDF/Markdown, generating diff reports, adding comments, and word count/AI-powered summaries.
- Supports common CLI and Python API workflows, with flexible document style options (default, business, academic).
- Comprehensive installation guidance for required Python and system-level dependencies.
- Auto-activates for a wide range of document-related tasks using keyword triggers.
Metadata
Frequently Asked Questions
What is TDOC Docx?
Word 文档全能处理技能 | Complete Word Document Processing Skill. 支持创建、读取、编辑、转换 Word 文档 | Create, read, edit, convert Word documents. 支持 .docx/.doc 格式、中文公文格式、表格、图片、tr... It is an AI Agent Skill for Claude Code / OpenClaw, with 365 downloads so far.
How do I install TDOC Docx?
Run "/install tdoc-docx" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TDOC Docx free?
Yes, TDOC Docx is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TDOC Docx support?
TDOC Docx is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TDOC Docx?
It is built and maintained by WenRichard (@wenrichard); the current version is v1.0.0.
More Skills