← Back to Skills Marketplace
mar-document-pro
by
MarjorieBroad
· GitHub ↗
· v1.0.0
· MIT-0
68
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install mar-document-pro
Description
文档处理技能 - 让 AI 能够读取、解析、提取 PDF、DOCX、PPT 等文档的关键信息，并通过 SkillBoss API Hub 进行 AI 智能分析与摘要。当用户要求分析文档、提取内容、总结报告时触发此技能。
Usage Guidance
Before installing or enabling this skill, consider the following:
- Metadata mismatch: the registry metadata does not declare the SKILLBOSS_API_KEY that the SKILL.md requires, nor does it list the Python packages the code examples use. Ask the publisher to correct metadata and provide a manifest or install steps (pip requirements) so you know what will run.
- Data privacy: the workflow extracts full document text and sends it to api.heybossai.com. Do not allow the skill to process sensitive, confidential, or regulated documents unless you trust SkillBoss and have reviewed their privacy/security policies.
- Runtime requirements: this is an instruction-only skill that assumes Python and multiple libraries are available. If you enable it, ensure it's run in a controlled environment with the required packages installed (or request the skill author add an install spec).
- Least privilege: supply a dedicated API key with limited scope for SkillBoss rather than reuse broad credentials, and rotate/revoke the key if you stop using the skill.
- Ask for clarification: request that the author update the registry to declare SKILLBOSS_API_KEY as primaryEnv, list required packages (requirements.txt), and state expected runtime (Python version) and any data retention behavior for the external API.
Given the metadata/instruction inconsistencies and the external data transmission, proceed only after those questions are answered and you are comfortable with the privacy trade-offs.
Capability Tags
Capability Assessment
Purpose & Capability
The SKILL.md describes a document-processing skill that extracts text/tables and calls the SkillBoss API — this matches the name/description. However, the registry metadata declared no required env vars or binaries while the SKILL.md requires SKILLBOSS_API_KEY and references multiple Python libraries (pdfplumber, PyPDF2, python-docx, python-pptx, openpyxl). The skill will thus fail or behave unexpectedly unless a Python runtime and those packages are available; that mismatch is incoherent.
Instruction Scope
Instructions are explicit about reading local files (PDF/DOCX/PPTX/XLSX), extracting contents, then sending the extracted text to https://api.heybossai.com/v1 via requests with the SKILLBOSS_API_KEY. This is consistent with the described purpose, but it means full document contents (potentially including sensitive data) are transmitted to a third-party service — a privacy/exfiltration risk inherent to the workflow and worth the user's consideration.
Install Mechanism
There is no install spec (instruction-only), which is lower supply-chain risk. However, the instructions rely on multiple Python packages but do not declare them or provide installation steps. That omission is an operational inconsistency (runtime dependencies are undeclared).
Credentials
SKILL.md requires SKILLBOSS_API_KEY (used to call the external API), which is proportionate to the stated third-party AI analysis. But the registry metadata does not list this required environment variable or mark a primary credential — a clear mismatch. The single API key requested is reasonable for function, but the metadata omission reduces transparency.
Persistence & Privilege
The skill is not always-enabled and does not request elevated system persistence or modify other skills. It is user-invocable and can be invoked autonomously per platform defaults; nothing in the package requests unusual privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mar-document-pro - After installation, invoke the skill by name or use
/mar-document-pro - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Document Pro - AI-powered document processing skill.
- Supports reading, extracting, and summarizing PDF, Word, PowerPoint, Excel, TXT, and Markdown files.
- Integrates with SkillBoss API Hub for AI-powered document analysis, summarization, and keyword extraction.
- Enables content extraction, format conversion, and structured summaries in Chinese.
- Provides example code for processing each supported format.
- Lists environment variable requirements and output formats.
- Documents limitations such as the need for OCR with scanned PDFs and limited handling of complex or image-based content.
Metadata
Frequently Asked Questions
What is mar-document-pro?
文档处理技能 - 让 AI 能够读取、解析、提取 PDF、DOCX、PPT 等文档的关键信息，并通过 SkillBoss API Hub 进行 AI 智能分析与摘要。当用户要求分析文档、提取内容、总结报告时触发此技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 68 downloads so far.
How do I install mar-document-pro?
Run "/install mar-document-pro" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is mar-document-pro free?
Yes, mar-document-pro is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does mar-document-pro support?
mar-document-pro is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created mar-document-pro?
It is built and maintained by MarjorieBroad (@marjoriebroad); the current version is v1.0.0.
More Skills