← Back to Skills Marketplace
aaiccee

U2-doc-parser

by aaiccee · GitHub ↗ · v1.0.5 · MIT-0
cross-platform ✓ Security Clean
655
Downloads
1
Stars
0
Active Installs
6
Versions
Install in OpenClaw
/install u2-doc-parser
Description
Parse documents using UniDoc API for conversion to Markdown or JSON format. Supports both synchronous and asynchronous parsing with automatic status polling.
Usage Guidance
This skill appears to do exactly what it says: it uploads the file you provide to the UniDoc UAT service for conversion and returns Markdown/JSON. Before installing or using it, consider: 1) Do not upload sensitive or confidential documents — the skill explicitly sends files to a third‑party UAT endpoint without requiring authentication. 2) If you need to use a private UniDoc instance, set UNIDOC_BASE_URL (and UNIDOC_API_KEY if required) in a controlled environment. 3) Run this in an isolated environment and inspect the script if you have stricter privacy requirements. 4) Ensure the 'requests' dependency is installed and, if running non-interactively, avoid using HTTP endpoints that cause the script to prompt for confirmation. If you want stronger privacy guarantees, obtain a trusted/production UniDoc endpoint with authentication or run an on-premise parser instead.
Capability Analysis
Type: OpenClaw Skill Name: u2-doc-parser Version: 1.0.5 The skill is a document parsing utility designed to convert various file formats to Markdown or JSON via the UniDoc API. While the tool uploads documents to an external UAT (User Acceptance Testing) environment (unidoc.uat.hivoice.cn) without authentication, this behavior is the explicitly stated purpose of the skill and is accompanied by prominent privacy warnings in SKILL.md, README.md, and the script's execution flow. The implementation in scripts/unidoc_parse.py demonstrates defensive programming, including path sanitization to prevent traversal attacks, file size limits, and restrictions against writing to sensitive system directories.
Capability Assessment
Purpose & Capability
Name and description (convert documents via UniDoc API) match the included files (README, SKILL.md, scripts/unidoc_parse.py). The skill requires no unrelated binaries or credentials; optional env vars (UNIDOC_BASE_URL, UNIDOC_API_KEY) are consistent with configuring the API endpoint.
Instruction Scope
Runtime instructions and the included Python script only perform operations consistent with the stated purpose: validate and read a user-supplied file, upload it to the UniDoc endpoints, poll status (for async), and fetch converted output. The README/SKILL.md explicitly warn that documents are uploaded to an external UAT endpoint and advise not to use sensitive documents.
Install Mechanism
No install spec; the skill is instruction+code only. It requires the standard 'requests' Python library (documented). No downloads from untrusted URLs or archive extraction are present in the manifest.
Credentials
The skill declares no required credentials. It optionally reads UNIDOC_BASE_URL and UNIDOC_API_KEY which are reasonable for configuring the service. The primary privacy concern is deliberate: the skill uploads files to an external UniDoc UAT server (no auth), which the documentation repeatedly warns about — this is expected for the skill but has privacy implications.
Persistence & Privilege
Skill is not always-enabled and does not request elevated or persistent system privileges. It does create output directories if needed and validates output paths, but it does not modify other skills or system-wide agent settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install u2-doc-parser
  3. After installation, invoke the skill by name or use /u2-doc-parser
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.5
Version 1.0.5 - Added a comprehensive README.md with usage instructions, privacy notice, and detailed options. - Included __pycache__/unidoc_parse.cpython-312.pyc (compiled Python bytecode) in scripts directory.
v1.0.4
- Added an important privacy notice warning users that all documents are uploaded to an external third-party API (https://unidoc.uat.hivoice.cn), with no authentication required. - Emphasized that the service should not be used for sensitive, confidential, or private documents. - Noted that users acknowledge their files will be uploaded to external servers by using the skill. - Clarified security, privacy, and authentication aspects throughout documentation.
v1.0.3
- Improved documentation for a clearer quick start and usage guidance. - Default output now prints to terminal; option added to save output to a file. - Output directory convention changed: `--output` now specifies file (not directory); when omitted, prints to stdout. - Updated example commands for clarity and typical use cases. - Removed sample files: .claude/settings.local.json, README.md, references/unidoc-notes.md.
v1.0.2
u2-doc-parser v1.0.2 - Added README.md for user guidance and quick reference. - Added references/unidoc-notes.md containing UniDoc API endpoint details and technical notes. - Added .claude/settings.local.json for local skill configuration. - Documentation now includes concise quick start, usage options, prereqs, and troubleshooting notes. - Introduced reference docs to support API/network troubleshooting and endpoint understanding.
v1.0.1
- Major documentation update: SKILL.md is now more comprehensive, with strict usage instructions, advanced troubleshooting, configuration steps, and clear error handling guidance. - Security and usage restrictions are explicitly documented: Only the UniDoc API and provided scripts should be used, with no alternatives or fallback parsing methods allowed. - Environment variable requirements and configuration workflow are now detailed, including instructions for extracting credentials and confirming setup. - Advanced examples and mode explanations (sync vs. async) have been added. - References and sample notes were removed from the repository.
v1.0.0
Initial release of u2-doc-parser. - Parse documents to Markdown or JSON using the UniDoc API. - Supports synchronous and asynchronous operation with automatic polling in async mode. - Handles multiple document types, including PDF, DOC, DOCX, and common image formats. - Command-line interface allows selection of output format, parsing mode, and output directory. - Designed for cloud-based conversion with automatic output organization.
Metadata
Slug u2-doc-parser
Version 1.0.5
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 6
Frequently Asked Questions

What is U2-doc-parser?

Parse documents using UniDoc API for conversion to Markdown or JSON format. Supports both synchronous and asynchronous parsing with automatic status polling. It is an AI Agent Skill for Claude Code / OpenClaw, with 655 downloads so far.

How do I install U2-doc-parser?

Run "/install u2-doc-parser" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is U2-doc-parser free?

Yes, U2-doc-parser is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does U2-doc-parser support?

U2-doc-parser is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created U2-doc-parser?

It is built and maintained by aaiccee (@aaiccee); the current version is v1.0.5.

💬 Comments