题库制作流水线：把备考资料变成本地刷题应用
题库制作流水线（@user_b5a543a8/quiz-bank-builder，v1.3.0，community 来源，education 分类）把 PDF、Word、网页、纯文本中的考试题目变成单文件本地刷题 HTML 应用。流水线覆盖文本提取、题目解析（内置八大坑对策）、答案六项体检、去重、多来源答案交叉校验、图片与表格题挂载、刷题应用构建、headless 回归测试。刷题应用包含进度持久化、错题本、SRS 复习回滚、背题模式、笔记联动、手动纠正答案、多选题。提供零代码路径：用户只给资料和确认样例，其余由 Agent 完成。全程本地运行，不联网、不依赖任何 API Key，数据只存本机浏览器。适合考证备考、考研考公、企业内训出题、老师做练习册。
Read More图片文字识别：本地离线 OCR 的 Agent Skill
图片文字识别（@user_43faedd6/image-ocr）是一个社区维护的本地离线 OCR Agent Skill，版本 0.3.6，属 office-efficiency 分类，不需要 API Key。它能在不联网、不上传的前提下，从图片、扫描件、多页 PDF 提取文字、数字、表格、代码和算式，支持中文 chi_sim、英文 eng 及可下载的其他语言包，并可将表格转 Markdown/CSV、代码截图转文本。适合截图、照片、扫描件、试卷、表单、图纸说明等无法复制文字的图片，也适合有隐私要求、不希望上传云端的场景。不适合可直接复制的电子文档、以手写体为主的图片（准确率有限）或需要联网 OCR/云端视觉的场景。官方资料未提供安装命令与配置字段，需以 SkillHub 页面为准。
Read MorePersonal Goals Pro：层级目标自动拆解与本地离线管理
Personal Goals Pro 是 SkillHub 社区 Skill（@user_f3bf9b16/personal-goals-pro，v1.0.9），面向年/季/月层级目标录入、每日定时自动拆解任务、OpenClaw 多渠道推送与月度复盘，数据本地离线存储且无需 API Key。文章说明核心能力、skillhub CLI 安装路径（含 Cursor/Codex 等 skills 目录）及适用场景与限制，并附官方 SkillHub 地址。
Read Moredsh-gsv-tts: DeepSeek Harness Text-to-Speech Plugin
The DeepSeek Harness voice reading plugin `dsh-gsv-tts` supports dual-mode speech synthesis: a cloud-based Edge mode for zero-configuration quick use, and a local GSV mode for offline voice cloning. Core features include one-click reading, automatic reading control, visual sound settings, voice marketplace downloads, and one-click engine start/stop management. It can be installed via the command line and allows one-click switching between the “Quick Experience” and “Local Professional” modes. Please note that Edge mode requires network access, while GSV mode requires a Python 3.10+ environment and may take additional time to load on first use.
Read MoreParakeet Voice Input for DeepSeek Harness: A Local Offline Voice Input Plugin
Parakeet Voice Input is a local speech-to-text plugin developed by vTRKA for DeepSeek Harness. By integrating the Parakeet and NeMo-Speech.cpp models, it allows users to record audio in Composer using a keyboard shortcut (Ctrl+E by default) or a button. All audio is processed locally and is not uploaded to external APIs. Installation requires running a script in PowerShell and restarting the application, and users must ensure that local port 8080 is not in use. This solution is suitable for developers who value privacy and offline operation.
Read More