← 返回 Skills 市场
MinerU Doc Parser
作者
MinerU-Extract
· GitHub ↗
· v0.2.1
· MIT-0
1010
总下载
6
收藏
2
当前安装
9
版本数
在 OpenClaw 中安装
/install mineru-ai
功能描述
MinerU AI document parser — intelligent document extraction powered by AI. Parse PDFs, scanned documents, images, Word files, PowerPoint slides, and web page...
安全使用建议
This skill appears to be a normal CLI wrapper for MinerU's document parsing service, but there are a few things to check before installing or using it:
- Expect that documents you parse are likely uploaded to MinerU's servers (token management and the site URL are referenced). Do not use it with sensitive or confidential documents unless you have verified MinerU's privacy/security policies.
- The SKILL.md mentions an environment variable (MINERU_TOKEN) and a config file (~/.mineru/config.yaml) but the registry metadata did not declare these. Verify how tokens are stored, file permissions, and whether tokens are encrypted or stored in plaintext.
- Confirm the npm package and GitHub repo: inspect the mineru-open-api package contents and the GitHub source (github.com/MinerU-Extract/mineru-ai) before installing globally. Prefer verifying package integrity (checksums, signed releases) and review the code that performs network uploads.
- If you need offline/local-only parsing, confirm the tool supports local-only mode; otherwise avoid using it for private documents.
If you want, I can: (1) fetch the mineru-open-api npm package metadata and popular-vote/comment history, (2) summarize the GitHub repo's README and code paths related to network I/O, or (3) draft safer usage instructions (e.g., run in an isolated VM, inspect config file contents).
功能分析
Type: OpenClaw Skill
Name: mineru-ai
Version: 0.2.1
The mineru-ai skill is a legitimate wrapper for the MinerU AI document parsing service, providing tools for converting PDFs and images into structured formats like Markdown. The SKILL.md file contains well-defined instructions for the agent to handle authentication, choose between extraction modes, and manage output directories safely. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found; the tool's behavior is consistent with its stated purpose of document processing via the mineru-open-api CLI.
能力评估
Purpose & Capability
Name, description, and required binary (mineru-open-api) match a CLI-based document parser. Supported formats, extraction modes, and npm/go install options are coherent with the stated purpose.
Instruction Scope
SKILL.md instructs the agent to run mineru-open-api commands including flash-extract, extract, crawl, and auth. It additionally documents token resolution that includes an on-disk config (~/.mineru/config.yaml) and an environment variable (MINERU_TOKEN). The registry metadata listed no required config paths or env vars, so the instructions read a file and environment state that were not declared. The instructions also imply sending documents/URLs to mineru.net endpoints (token creation at mineru.net), but do not explicitly state privacy/where processing occurs.
Install Mechanism
Install is via npm package or go install from a GitHub repo — standard mechanisms for a CLI. Both create the expected binary name mineru-open-api. No high-risk download URLs or extract-from-unknown-host actions are present.
Credentials
Registry metadata lists no required env vars, yet SKILL.md documents MINERU_TOKEN and interactive auth. The skill will accept an API token and can read ~/.mineru/config.yaml; requesting/using tokens is reasonable for an API service, but the lack of declaration is an inconsistency. Also, processing likely involves uploading documents to MinerU servers — requiring a token is proportionate for production use but increases sensitivity of data sent.
Persistence & Privilege
Skill is user-invocable and not always-enabled. It does not request permanent platform privileges or claim to modify other skills. Normal autonomous invocation is allowed by default.
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 mineru-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/mineru-ai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
v0.2.1
Fix: republish with complete SKILL.md content (previous publish had truncated CLI documentation)
v0.2.0
SEO optimization: new AI-focused description with 200+ words, bilingual keywords, trigger phrases for AI document parsing search queries
v1.0.10
- No file changes detected; maintenance version release.
- Documentation, description, features, and usage unchanged from previous release.
- No new features, bug fixes, or command updates included in this version.
v1.0.9
- Added table and formula recognition support to token-free flash extraction mode.
- Updated documentation to reflect that flash-extract now recognizes tables and formulas in quick extraction.
- Adjusted comparison tables to show feature parity between flash-extract and extract for table/formula recognition.
- Clarified best use cases for flash-extract and extract modes.
v1.0.8
Version 1.0.8 (no file changes detected):
- No detectable changes to files or documentation in this release.
- All features and documentation remain the same as in the previous version.
v1.0.7
mineru-ai v1.0.7
- Documentation streamlined for conciseness and ease of use, especially in the Core workflow section.
- No changes to code or binaries; documentation only.
- Command usage instructions remain unchanged.
- All features and limits are consistent with previous versions.
v1.0.6
**Improved extraction workflow and error handling for MinerU CLI.**
- Updated core workflow to always try `flash-extract` first for any input (local file or URL), for faster and simpler usage.
- Documented how to interpret `flash-extract` exit codes and next actions (e.g., when to switch to `extract` with a token).
- Clarified difference between document URL handling and web page extraction (`flash-extract` vs `crawl`).
- Enhanced troubleshooting guidance for error cases in the extraction flow.
- Improved workflow steps and user instructions for better clarity and usability.
v1.0.5
- Added npm and Go installation instructions for mineru-open-api; now supports install via npm or go install.
- Updated metadata to reflect new install methods, replacing previous direct download scripts.
- Removed curl/PowerShell script installation instructions.
- No CLI feature changes.
v1.0.3
mineru 1.0.3
- Added CONTRIBUTING.md to guide community contributions.
- Added _meta.json for enhanced metadata management.
- Overhauled SKILL.md to provide detailed CLI-based instructions, including installation, usage, and feature comparison for flash-extract and extract modes.
- Expanded documentation on supported file types, output formats, command-line flags, web crawling, and batch processing.
- Clarified extraction limits, setup steps, and model selection guidance for improved user onboarding.
元数据
常见问题
MinerU Doc Parser 是什么？
MinerU AI document parser — intelligent document extraction powered by AI. Parse PDFs, scanned documents, images, Word files, PowerPoint slides, and web page... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1010 次。
如何安装 MinerU Doc Parser？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mineru-ai」即可一键安装，无需额外配置。
MinerU Doc Parser 是免费的吗？
是的，MinerU Doc Parser 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
MinerU Doc Parser 支持哪些平台？
MinerU Doc Parser 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 MinerU Doc Parser？
由 MinerU-Extract（@mineru-extract）开发并维护，当前版本 v0.2.1。
推荐 Skills