闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > mineru-pdf
m

本地PDF解析

技能标识：mineru-pdf

Parse PDFs locally (CPU) into Markdown/JSON using MinerU. Assumes MinerU creates per‑doc output folders; supports table/image extraction.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.0.0
检测标记
后台标记通过
免费
免费获取
2
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

本地PDF解析

MinerU PDF

概述

使用MinerU（CPU）在本地解析PDF文件。默认输出格式为Markdown + JSON。仅在需要时使用表格/图片。

快速开始（单个PDF）

bash

在技能目录下运行

./scripts/mineru_parse.sh /path/to/file.pdf

可选示例：
bash
./scripts/mineru_parse.sh /path/to/file.pdf --format json
./scripts/mineru_parse.sh /path/to/file.pdf --tables --images

何时阅读参考文档

如果参数与你的封装器不同，或者你需要高级默认设置（后端/方法/设备/线程/格式映射），请阅读：
  • - references/mineru-cli.md

输出约定

  • - 输出根目录默认为 ./mineru-output/。
  • MinerU会在输出根目录下创建每个文档的子文件夹（例如 ./mineru-output//...）。

批处理

默认为单个PDF解析。仅在明确要求时才实现批量文件夹解析。

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 mineru-pdf-parser-clawdbot-skill-1776389723 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 mineru-pdf-parser-clawdbot-skill-1776389723 技能

通过命令行安装

skillhub install mineru-pdf-parser-clawdbot-skill-1776389723

下载

⬇ 下载 mineru-pdf v1.0.0（免费）

文件大小: 5.63 KB | 发布时间: 2026-4-17 14:43

v1.0.0 最新 2026-4-17 14:43
Initial release of mineru-pdf skill.

- Parse PDFs locally using MinerU (CPU) with support for Markdown and JSON output.
- Optional extraction of tables and images when specified.
- Assumes per-document output folders created by MinerU.
- Provides simple command-line usage with customizable output format and options.
- Batch processing is not enabled by default; only implement upon request.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部