Bundle
dsh-maclens
Bridge Apple's on-device Vision framework (macOS) into DeepSeek Harness: OCR, image classification, face detection, and document layout as local dsh tools. No network, no API key, no daemon.
Harzva
Browse
138 results
Bundle
dsh-view-image
让 dsh 用独立的 OpenAI 兼容视觉模型读图：主对话历史只保留纯文本描述，图片字节不进上下文，纯文本模型也能读图。
johnoooooo
Bundle
dsh-socrates
苏格拉底诘问式开发伴侣：提示闸门（实现意图模糊时强制澄清）+ 高危操作闸门（不可逆命令前提问）+ socratic 技能 + 苏格拉底审查者 persona preset。让 AI 不再顺从，让实现恰好是你想要的。
Paloma966
Bundle
dsh-plugin-deepseek-vision
DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。
deepseek-vision-mcp contributors
Bundle
dsh-baidu-ocr
Baidu cloud OCR (PaddleOCR-VL + Unlimited-OCR) for DeepSeek Harness Web: drag images/PDFs in, OCR to markdown, write results as local files.
pipiwolve
Bundle
xby-ocr-biz-license
识别营业执照的统一社会信用代码、名称、法定代表人、注册资本、成立日期、经营范围、登记机关和住所地址。
xby-skill
Bundle
xby-ocr-vehicle-license
识别机动车行驶证的号牌号码、车辆类型、所有人、住址、品牌型号、发动机号码、车辆识别代号等信息，支持自动方向检测和主副页过滤。
xby-skill
Bundle
xby-ocr
兼顾速度与精度的文字识别。输入包含文本的图像，自动检测并识别内容。适用于各类文档、广告牌、屏幕截图等场景。
xby-skill
Bundle
xby-ocr-pass
识别港澳通行证、台湾通行证的通行证号码、姓名、性别、出生日期、有效期、签发地点等信息，支持MRZ机读码解析。
xby-skill
Bundle
xby-ocr-captcha
输入常见验证码图片，返回验证码文本内容。
xby-skill
Bundle
dsh-image-router
DeepSeek Harness plugin: analyse images out of band with a vision model — pasted images are digested into text before admission and a describe_image tool covers image paths, all without ever changing the session's model.
zhiwuli0228
Bundle
dsh-math-input
Zero-token offline math input for DeepSeek Harness: handwriting recognition, screenshot OCR, LaTeX editor, and inline LaTeX rendering.
xiaxi626
Bundle
dsh-linkdigest
LinkDigest for DeepSeek Harness: mounts the remote LinkDigest MCP (https://linkdigest.dev/mcp) via the in-box @deepseek-ai/dsh-mcp-client bridge — turn a Xiaohongshu, Douyin, TikTok, YouTube or X link into text an agent can read.
jcaiagent7143-ui
Bundle
dsh-file-upload-local
Local file-upload plugin for DeepSeek Harness: a paperclip button and drag-and-drop that store files per-session under .dsh-uploads/<sessionId>/, plus a read_document tool that pages text and OCRs images (tesseract.js) so a text-only model can still read screenshots.
lubenweimeiyoukaig
Bundle
dsh-pdf-to-word
DeepSeek Harness plugin: PDF→Word (.docx) conversion with layout fidelity (fonts/tables/images/borders), OCR scan mode, and optional multimodal LLM verification. Registers the pdf_to_word model tool.
dy395769511-star
Bundle
vision-exp-tile
为 deepseek-v4-flash-vision-exp 量身定制的大图智能识图插件：整图预检 → 本地 OCR+像素网格（文字）+ 兴趣点按比例切块（最长边 800）→ 汇总；保留全图 800x800 网格切块模式。不代为统计/不显示 token 与费用，实际计费以 DeepSeek 官方 API 平台账单为准。v0.4.3：仓库元数据修复 / 计费表述诚实化 / 新增隐私与数据说明 / 过期临时产物清理。
Nicholaskin
Bundle
dsh-markitdown
Microsoft MarkItDown as a DeepSeek Harness tool: convert PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB, or a URL into Markdown the model can read.
jiekesu967
Bundle
@goodandready/dsh-vision-bridge
Flagship multimodal vision hub for DeepSeek Harness: ~40 tools, PDF drag-and-drop, LaTeX formulas, complex tables, QR codes, UI flow diagrams, and multi-model consensus.
GooDAnDReaDY