image-analysis-skill
SKL-666666
图片结构化分析技能:双引擎OCR+形状/表格/图标/布局识别,让纯文本模型看懂图片
DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。
320 个项目,匹配「deepseek-harness」
SKL-666666
图片结构化分析技能:双引擎OCR+形状/表格/图标/布局识别,让纯文本模型看懂图片
Su2uka111
Document drag-and-drop plugin for DeepSeek Harness: PDF/Word/Excel/text auto-parsed with dual-track context (inline + doc_read), native WinRT OCR for scans. Zero upstream changes, hot-injectable. | DeepSeek Harness 文档拖拽读取插件:PDF/Word/Excel/文本自动解析,双轨上下文(内联 + doc_read 按需检索),扫描件原生 WinRT OCR。零修改上游,运行时热注入。
TiankunDai
让你能通过deepseek harness调用LM studio加载的本地视觉模型
Tieboyh
Index-free cross-agent session search for DeepSeek Harness
Totoro-qaq
Human-editable notes, todos and documents for DeepSeek Harness, with search, tables, attachments, export and optional agent collaboration.
TwistedRiCen
DSH-native Vision Evidence bridge for text-only reasoning models with native image attachments and strict multi-image validation.
U-Illll
Memory retrieval plugin for DeepSeek Harness (dsh): wiki double-link memory graph with 9 tools — hybrid search, read, link-scan, remember, forget, compile, health-check, resident retriever subagent
YinjiangCN
Configurable FTP file server for DeepSeek Harness with a browser settings panel (zero-dependency FTP core).
YuLee-314
DeepSeek Harness 视觉补全:孪生路由解锁原生图片体验,本地 Ollama 请求层看图,零云端依赖。Vision twin + local agentic vision tools for DeepSeek Harness.
aijunjiang
Give your DSH agent eyes via any OpenAI-compatible vision model - 11 provider presets (Doubao/Qwen-VL/GLM-V/OpenAI/Gemini/Ollama...), capability checkboxes that inject live prompt guidance, and analysis of images the user drops into the chat; the agent writes its own observation prompt, and base64 never enters its context.
ang-XWBWZ
Local-first knowledge retrieval engine for AI agents — BM25, semantic search, reranking, MCP, Pi Agent and DeepSeek Harness integration.
bentong-chain
A DeepSeek Harness (DSH) floating workspace directory-tree plugin. Install with `dsh plugin add`, drag-drop file paths into chat, lazy-load, and auto-follows workspace switches.
bocha-ai
DeepSeek Harness Web Search Plugin
brickmaker
为 DSH Web 提供当前工作区文件树右侧栏
dawsondx
DSH 对话报告化分享插件:生成带封面、摘要统计与章节排版的精美报告,导出为 PNG 图片 / 单 HTML 文件 / PDF。
dhb861832993-star
Local knowledge base for DeepSeek Harness: zero-dependency SQLite FTS5 index for markdown/text/code/web pages, source-cited retrieval, session experience library, interactive kbquery Web panel + knowledge galaxy.
dingchenhui0618-arch
Bundled imagegen skill for DeepSeek Harness: generate or edit raster images from the agent through any OpenAI-compatible GPT Image endpoint.
faettt
Tavily web search provider for DeepSeek Harness (DSH): provider + tavily_search tool + settings card with enable switch
fengs2021
给 DSH 文本模型装眼睛:图片自动调用 mmx(MiniMax VLM)识别,识别结果注入模型上下文
fulander0301
Model-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.
iasmndjxjz
DSHA 论文阅读器插件:三栏阅读(左目录/中黑底论文/右实时 Agent 对话)+ 右栏停靠模式 + pdf.js 渲染与文字抽取
iskshadow195563
📁 右侧可折叠的 DeepSeek 上传文件管理面板(dsh 插件):列出/复制/清理 DeepSeek Files API 上传的图片,密钥零暴露,一条命令安装
jmjmj009gt
Zero-dependency vision OCR/Q&A toolkit (CLI + local web GUI) for OpenAI-compatible VLMs: Zhipu GLM, Qwen, OpenAI, OpenRouter, SiliconFlow
kanchengw
Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, and GUI automation, through layered evidence memory and cache.