agentmods.dev

deepseek-design-vision

deepseek-design-vision is a skill for Codex from ningyougan/deepseek-vision-mcp. It costs 80 tokens per session (654 once invoked), scanned A, original, MIT.

A visual design reader that turns UI screenshots, Figma exports, prototypes, or image links into written layout details and front-end code.

In plain words
What is it for?
Use it to recreate web pages or WeChat mini-program screens from designs, answer visual questions, and check accessibility details such as focus states and contrast.
Why use it?
It reduces the guesswork of rebuilding a page from an image by identifying its colors, text, spacing, components, and responsive behavior.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 0repo 3mo ago A scan 80 tokens original MIT

Good fit Use it to recreate web pages or WeChat mini-program screens from designs, answer visual questions, and check accessibility details such as focus states and contrast.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ningyougan/deepseek-vision-mcp/deepseek-design-vision
View source ↗ ningyougan/deepseek-vision-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ningyougan/deepseek-vision-mcp --skill deepseek-design-vision
Clone the repo
git clone --depth 1 https://github.com/ningyougan/deepseek-vision-mcp

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deepseek-design-vision

README.md
[![agentmods](https://agentmods.dev/badge/skills/ningyougan/deepseek-vision-mcp/deepseek-design-vision/github.svg)](https://agentmods.dev/skills/ningyougan/deepseek-vision-mcp/deepseek-design-vision)
Your own site
<a href="https://agentmods.dev/skills/ningyougan/deepseek-vision-mcp/deepseek-design-vision"><img src="https://agentmods.dev/badge/skills/ningyougan/deepseek-vision-mcp/deepseek-design-vision/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deepseek-design-vision

Your own site · 80×15
<a href="https://agentmods.dev/skills/ningyougan/deepseek-vision-mcp/deepseek-design-vision"><img src="https://agentmods.dev/badge/skills/ningyougan/deepseek-vision-mcp/deepseek-design-vision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00654
Opus 5.5 $0.00032 $0.00262
Sonnet 5.5 $0.00016 $0.00131
Haiku 4.5 $0.00008 $0.00065

Measured 2mo ago against content hash 6b84ab650a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deepseek-design-vision scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/deepseek-design-vision/SKILL.md · 37 lines

What it actually says

设计稿识别与前端还原

工作流

  1. 确定图片：使用用户给出的本地路径或 URL；若图片在剪贴板或聊天里，先保存为本地文件再继续。

  2. 用本地视觉服务识别设计稿（DeepSeek 文本模型不能直接看图）：

    cd __PROJECT_DIR__
node cli.js <图片路径> --mode both --stack <技术栈>

    技术栈按项目选择：html+css、react+tailwind、vue3+tailwind、微信小程序 等。

  3. 若环境已注册 deepseek-vision MCP 服务，优先调用 analyze_design（参数 image/mode/tech_stack），通用图片问答调用 ask_vision。

  4. 使用 CLI/MCP 返回的结构化规格（layout、colors、typography、spacing、components、responsive、accessibility）实现代码；不要凭空添加设计稿中没有的模块，规格有矛盾时先向用户确认。

运行环境

  • 视觉服务目录：__PROJECT_DIR__
  • 在线服务：在 __PROJECT_DIR__/.env 中配置 HF_TOKEN 或 VISION_API_KEY；默认模型 Qwen/Qwen3-VL-8B-Instruct，模型不可用时可切换 VISION_MODEL=Qwen/Qwen2.5-VL-7B-Instruct。
  • 本地 Ollama：在 __PROJECT_DIR__/.env 中配置 VISION_PROVIDER=ollama、OLLAMA_API_BASE=http://127.0.0.1:11434、OLLAMA_MODEL=qwen3-vl:8b，无需 API Key。
  • Ollama 的 qwen3-vl:8b 是思考版，服务会自动应用 /no_think workaround；追求更快可把 OLLAMA_MODEL 改成 qwen3-vl:8b-instruct。
  • 如有代理可配置 VISION_PROXY。

编码要求

  • 精确还原颜色、圆角、间距、字号、阴影，不随意替换。
  • 移动端优先，参考断点 375px / 768px / 1280px。
  • 使用语义化标签，补充对比度、focus 状态、aria。
  • 图标优先使用内联 SVG 或组件库图标，不依赖外链图片。
  • 覆盖 hover、active、focus、loading、empty、error 等状态。
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 37 lines · 80 tokens per session scan A 6b84ab650a54

Subscribe to this mod's changes

deepseek-design-vision is a skill published in the GitHub repository ningyougan/deepseek-vision-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 654 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Design and UXFrontend
Related

deepseek-design-vision compared with skills from other repositories

deepseek-design-vision next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deepseek-design-visionningyougan/deepseek-vision-mcpSkill03mo agoMITA80Codex
webgl-holographic-foilnexu-io/open-designSkill107ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill107ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill107ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10k2d agoApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code