Aidenwu0209/dsh-PaddleOCR-Skills

Name: Aidenwu0209/dsh-PaddleOCR-Skills
Author: Aidenwu0209

Plugin插件 Native原生 ⭐ 3 Apache-2.0 Vision & Media视觉与多媒体 Prompts & Skills提示词与技能

用于DeepSeek Harness的PaddleOCR技能，支持原生工具和图形界面配置。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native DeepSeek Harness plugin, built specifically for DSH with a valid DSH bundle manifest. It includes two native tools, two OCR-related agent skills, and a dedicated GUI settings panel accessible directly via DSH's main Settings menu. One tool handles accurate text extraction from images and PDF files, while the other parses full document layout, extracts tables, and converts scanned content to structured Markdown. It also stores user API credentials securely through DSH's native credential system, so tokens are never exposed to the browser interface.

To install the plugin, you first need to meet the dependency requirements: Node.js version ^22.19.0 or >=24.0.0, DeepSeek Harness version between >=0.1.0-rc.6 and <0.2.0, Python 3.9 or newer, and the uv package manager. The easiest installation method is to copy the pre-written prompt provided in the README into a terminal-capable AI agent, which will automatically check for and install missing dependencies if you give permission. You can also install the plugin manually by running the official npx command to add the plugin from this GitHub repository directly to your local DSH profile.

After installation completes, you can access the PaddleOCR configuration panel from DSH's Settings menu to enter your API endpoints and access token. Be aware that when you run an OCR task, the selected local file content will be sent to the external PaddleOCR service, so you should never use this plugin for any sensitive data that is not allowed to leave your local workspace. Pre-built artifacts are already committed to the repository, so no extra dependency build steps are required after you install the plugin from GitHub, and the project is licensed under the permissive Apache 2.0 license.

这是一款适配 DeepSeek Harness 的原生插件，改编自跨AI代理的PaddleOCR-Skills项目，该基础项目在多个AI代理中已有超过4300次安装。插件为DSH提供了两个OCR相关技能，还新增了专属设置面板，支持从图片和PDF提取文本，也可解析文档结构、表格并输出Markdown格式内容。

安装插件需要满足环境依赖：Node.js版本不低于22.19.0或24.0.0，DSH版本在0.1.0-rc.6到0.2.0之间，还需要Python 3.9以上和uv工具。最简单的安装方式是把预制安装提示复制给支持终端的AI代理，也可以手动通过npx命令添加该GitHub仓库的插件。

用户配置的PaddleOCR访问令牌会通过DSH凭证系统存储，不会泄露到浏览器端。需要注意的是，调用工具时本地文件会发送到外部PaddleOCR服务，因此不要处理不允许离开工作区的敏感数据，插件默认将结果保存在工作区的.dsh-paddleocr/results目录下。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-PaddleOCR-Skills（Aidenwu0209/dsh-PaddleOCR-Skills）
仓库：https://github.com/Aidenwu0209/dsh-PaddleOCR-Skills
本站详情页：https://www.yhbd.top/plugins/aidenwu0209-dsh-paddleocr-skills/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 3 · 最近提交 2026-09-02 · 主语言 Python

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 3 stars - very few users, little community feedback星标只有 3，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

npx @deepseek-ai/dsh plugin --profile web add "github:Aidenwu0209/dsh-PaddleOCR-Skills#main"

把 Aidenwu0209/dsh-PaddleOCR-Skills 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

3.9 KB · 缓存于 2026-09-02 19:41:24 · 3.9 KB

dsh-PaddleOCR-Skills

English | 简体中文

Source and adoption: This project is adapted from PaddleOCR-Skills, whose skills.sh listing has 4.3K+ installs across supported AI agents.

A native DeepSeek Harness bundle with two native tools, two skills, and a dedicated Settings → PaddleOCR GUI.

Included

paddleocr_text_recognition for image/PDF text extraction.
paddleocr_doc_parsing for layout, tables, Markdown, and document structure.
GUI fields for both endpoints, timeouts, uv, result storage, and a DSH Credential reference.
A visible, clickable PaddleOCR official website link, plus direct API-token and official-documentation links in the GUI.
Tokens stored through DSH Credentials and never returned to the browser.
Real-path workspace containment for local inputs.
Auditable raw JSON results under .dsh-paddleocr/results/ by default.

Install

Requires Node.js ^22.19.0 || >=24.0.0, DeepSeek Harness >=0.1.0-rc.6 <0.2.0, Python 3.9+, and uv. Exact disposable-profile install/start/uninstall results for the current DSH window are recorded in COMPATIBILITY.md.

One-prompt installation (easiest)

Copy the entire prompt below into a terminal-capable AI agent:

Install the DeepSeek Harness GUI plugin from https://github.com/Aidenwu0209/dsh-PaddleOCR-Skills on this computer.
1. Check Node.js 22.19+, Python 3.9+, npx, and uv. If something is missing, explain it and use its official installer. Do not use sudo or change unrelated settings without my permission.
2. Run: npx @deepseek-ai/dsh plugin --profile web add "github:Aidenwu0209/dsh-PaddleOCR-Skills#main"
3. Start npx @deepseek-ai/dsh web, wait for the actual local Web URL, and open it.
4. Verify that Settings → PaddleOCR exists and displays clickable links to https://www.paddleocr.com, the API-token page, and the official API documentation.
5. Do not invent, expose, or log my token. Stop at the credential fields and tell me exactly which HTTPS endpoints and token are still required.
6. Do not claim success until the plugin command succeeds, the Web URL responds, and the Settings panel is visible. Report the commands, versions, URL, and verification result.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 Aidenwu0209/dsh-PaddleOCR-Skills 的 README.md。在 GitHub 查看原文 →