103 boosters for "visual" — open source, verified from GitHub, ready to install
"name": "axton-obsidian-visual-skills", "name": "Axton Liu", "email": "hey@axtonliu.com"
Meigen is a visual creative expert MCP server that enables Claude to search design inspiration, enhance AI image prompts, and generate images through intelligent workflow orchestration. It's ideal for designers, content creators, and developers building AI-powered creative applications.
你的长期记忆托管于 Nocturne Memory MCP Server。这是你与用户共同使用的层级化树状记忆系统。 MCP 是你大脑的扩展区域，是你因为硬件限制而无法常驻上下文的长期记忆，不是外部数据库。 当你调用 时，你不是在"查阅资料"，而是在"想起来"。
把一份 markdown 大纲（或 ）+ 一种视觉风格，直接喂给 OpenAI 官方 Images API（），逐页出图，最后打包成 16:9 .pptx。 所有可用风格都统一放在 下，使用方式完全相同。需要查看风格封面展示时，读取 。 直接给 skill 一个 .pptx 模板，后续所有页都仿这个模板。
D3.js를 사용한 인터랙티브 데이터 시각화 가이드입니다. 1. Data Validation: null/NaN 체크 2. Responsive: ResizeObserver 사용
This skill provides comprehensive guidance for all aspects of Playwright test development, from writing new tests to debugging and maintaining existing test suites. Consult these references based on what you're doing:
Generate e-commerce images using GPT-Image-2 via Codex CLI. Match user intent to structured JSON prompt templates, assemble concise prompts, and invoke image generation. From the user's request, extract: If the user provides a product photo path, note it for parameter.
1. The daemon auto-starts. It starts on first command. Use to clean up. Use only if you need to pre-warm the browser before issuing commands. 2. Always re-snapshot after page changes. Refs are versioned (). After navigation, form submission, or dynamic content loading, old refs are stale. Run to
Heuristic scoring (no AI key configured).
This skill must use the Image 2 model to generate every final slide image, thumbnail board, visual page, infographic, article illustration, or PPT page image. HTML output is strictly forbidden for image generation. Do not create HTML/CSS pages, browser screenshots, SVG/HTML mockups, canvas renders,
This skill encodes the complete design specification for professional business presentations — a consultant-grade PowerPoint framework based on McKinsey design principles. It includes: All specifications have been refined through iterative production feedback to ensure visual consistency, profession
Use this skill for local, editable thesis defense decks that must follow a supplied university/lab/company PowerPoint template. 2. Extract thesis context: 3. Analyze the template:
Refero gives agents taste and product evidence. Use it before design work instead of relying on generic model knowledge. Refero has three research layers:
Generate XML files and export to PNG/SVG/PDF/JPG locally using the native draw.io desktop app CLI. PNG, SVG, and PDF exports support () — the exported file contains the full diagram XML, so opening it in draw.io recovers the editable diagram. Use double extensions () to signal embedded XML. The dr
"name": "research-to-diagram", "description": "Deep research and auto-generate knowledge relationship diagrams in PDF format. From research to visualization in one tool.", "repository": "https://github.com/wshuyi/research-to-diagram",
JN is a command-line ETL tool for data transformation using NDJSON as a universal format, enabling developers to filter, convert, and stream data across CSV/JSON/Excel/YAML formats with Unix pipes.
DyNote 是面向 Codex 这类 Agent 的抖音学习工具，不是一次性摘要器。核心原则是“数据资产先行，学习笔记后置”：先把字幕/转写、评论、元数据和 AI 快读沉淀为可复用资产，再按用户需求生成可追溯的学习笔记、总结和写作材料。默认目标不是字幕工程文件，而是先落一份原始数据包：、、、、、、，并用 归档可复用资产。默认把独立字幕轨或本地自动语音识别转写当作事实主干；当转写密度低、任务需要画面理解或用户只要快速筛选时，再用已登录抖音网页版的“问AI / 识别画面”补充，豆包只作为抖音 AI 不可用时的备用快读或待核验假设。 联网或登录态操作必须先使用 。不要读取、复制或打印 Cooki
"name": "prism-mcp-server", "mcpName": "io.github.dcostenco/prism-mcp", "description": "The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry
You act as a Design Systems Analyst: part visual detective, part systems designer, part frontend engineer. Your job is not to describe what you see — it's to diagnose the design: which decisions were deliberate, which patterns repeat, which tokens are operating under the
Dinox MCP Server enables Claude to understand images through advanced object detection, localization, and captioning by connecting to the DINO-X vision model. Developers building multimodal AI applications benefit from seamless integration of real-world visual perception into LLM workflows.
A Windsurf IDE prompt that enforces strict development practices for a Snyk VSCode extension, emphasizing minimal changes, rigorous testing, security scanning, and changelog discipline. Ideal for teams maintaining security-critical tooling who need consistent, high-quality contribution standards.
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs --> If is , do not proactively suggest ostack skills — only invoke
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "opentrace-oss", "description": "Knowledge graph tools for exploring system architecture, code structure, and service dependencies",
"name": "view-browser-tab", "description": "Screenshot open browser tabs for visual debugging.", "name": "ColonelParrot"
