文件与数据
技能
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
agent
agent-skills
claude-code
codex
文件与数据
插件
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
deepseek-harness
dsh
dsh-plugin
multimodal
文件与数据
技能
[dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
agent-skills
agent-vision-toolkit
computer-vision
deepseek
文件与数据
插件
Toward Autonomous Scientific Discovery
ai-agents
ai-scientist
auto-research
dsh-plugin
文件与数据
插件
专门为 agent 打造的开源 agent 搜索工具,具备 200+的搜索源及多语言搜索能力,覆盖中文/英文/学术/代码/购物/金融/新闻/百科。
academic-search
agent-tools
ai-agent
deep-research
文件与数据
完整应用
The AI analyst that shows its work. Runs Python and R on your own machine, and traces every chart back to the code behind it.
ai-agents
business-analytics
business-intelligence
claude-science
文件与数据
技能
专利侵权分析系统 —— 输入专利公开号,产出竞品侵权分析报告;同时打包成 skill,可被任意 agent(dsh, codex, claudecode 等) 调用。
agentic-ai
claim-chart
claude-code
claude-code-skill
文件与数据
技能
Package manager for AI agent assets — 42 skills, 5 CLIs, 1 plugin. Skills for AI/LLM agent engineering, eval-driven dev, spec-driven dev, database (MySQL/PG/Redis/Kafka/Mongo/Oracle/NL2SQL), K8s/Docker diagnostics, infra ops (Dify/Nexus/Harbor/SonarQube) & docs/patent. Runtimes: Codex, Claude Code, Cursor, Kiro, DSH.
agent-framework
agent-skills
ai-agents
claude-code
文件与数据
技能
Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kolors + U1 Fast generation. No keys in repo.
agent-skills
deepseek-harness
dsh-plugin
image-generation
文件与数据
插件
本地优先的文献知识库 RAG(DeepSeek Harness 插件):混合检索正文与图注,把模糊记忆定位到具体段落与图表,DOI 一键直达原文。Local-first literature RAG for DSH — turn a fuzzy memory into an exact passage/figure, one-click DOI to source.
deepseek-harness
dsh
dsh-plugin
knowledge-base
文件与数据
技能
Agent-agnostic workflow skill for maintaining Obsidian knowledge bases
agent-skill
ai-agent
codex
dsh-plugin
文件与数据
插件
FormatForge — DeepSeek Harness plugin: drag any file (PDF/DOCX/XLSX/EML…, 30+ formats) into dsh and it becomes AI-readable structured data. npm: @tianbuyu-wwx/dsh-formatforge
ai-tools
cordis
deepseek-harness
document-converter
文件与数据
技能
DSH Director Toolkit is a DeepSeek Harness plugin for 3D artists, technical designers, and creative coders. Paste a half-formed idea, a reference note, or a portfolio caption and get a compact direction pack for Blender, Three.js, Houdini, or C4D.
agent-skills
agent-vision-toolkit
blender
computer-vision
文件与数据
插件
该仓库暂未提供项目说明。
deepseek
deepseek-harness
dsh
dsh-plugin
文件与数据
插件
Hermes Tool Repair Skill - deterministic tool call repair for LLM agents. Catches common JSON formatting mistakes open models make and fixes them before dispatch, with repair notes that teach the model to self-correct.
agent-harness
bash
claude-code
cordis
文件与数据
技能
PaddleOCR skills for DeepSeek Harness with native tools and GUI configuration
agent-skills
deepseek-harness
dsh
dsh-plugin
文件与数据
技能
reSanity 散修 — 面向散户投研的证据搜索与逻辑梳理 Skill:核查一手资料,拆解题材到收入、利润和现金的传导链,标注证据与推断边界。
agent-skills
ashare
claude-code
codex
文件与数据
技能
将 Markdown 转换为符合学术规范的 Word 文档 skill,支持三线表、图题/表题自动编号、页码、页眉等学术论文排版规范。
agent-skills
docx
dsh-plugin
markdown
文件与数据
插件
给纯文本大模型装上原生视觉:流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.
ai-proxy
claude-code
codex
deepseek
文件与数据
技能
DSH Skill: 用本机 GPU 上的 ComfyUI + Z-Image Turbo 离线生图(零 API 费用),含显卡能力自检、文生图与局部重绘 CLI
comfyui
deepseek-harness
dsh
dsh-plugin
文件与数据
插件
GLM-4.6V 图像理解 MCP:识图/OCR/图表解析,原生接入 DeepSeek Harness(dsh-mcp-client),也兼容 Codex/Cline 等
codex
dsh-plugin
glm
image-understanding
文件与数据
插件
Scene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。
deepseek-harness
dsh
dsh-plugin
local-ai
文件与数据
技能
Codex skill for removing gray backgrounds from scanned PDFs without changing resolution or anti-aliased text.
codex-skill
deepseek-harness
dsh
dsh-plugin
文件与数据
技能
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
agent-skills
deepseek-harness
dsh-plugin
image-analysis