Art & Design

Grok Build skill: audit, validate, and improve existing (brownfield) codebases with assumption-aware analysis and optional PR execution

Website visual cloning skill for Claude Code — 6-phase process: recon, foundation, spec per section, parallel build, assembly, screenshot QA.

VeyraSkills — A curated collection of Claude Code skills for founders, developers and AI builders

🎬 Control and automate your entire self-hosted media stack with deep integration for library, viewing, requests, downloads, and Plex management.

Manage and automate Obsidian vaults from the command line with 100+ commands and direct file access for efficient workflows.

Build AI-driven UI collaboration with agent-browser, Figma MCP, and Lucid to turn wireframes into code that matches your design system

Build Claude Code from source maps with preserved @ant/* sources for custom, inspectable CLI builds

Transcribe Mandarin and English speech with this robust end-to-end ASR model designed for diverse dialects and complex acoustic environments.

Bypass bot detection with a custom Chromium build featuring C++ source-level fingerprint modifications. Drop-in replacement for Playwright and Puppeteer.

Rarefriend CRM — MCP server for Claude, Cursor, and any MCP client

Cross platform graph models allowing real time edge deployments to compute image segmentation paths with low overhead.

Tooling setups giving asset processing agents the simple, scalable skill to remove backgrounds from batches of product images automatically.

State-of-the-art 2D and 3D face analysis tools mapped to automated workflows for swift identification and profile alignment.

Enables agents to modify structural coordinates, material attributes, and camera pathways inside interactive 3D spaces.

Canvas-based whiteboard tool coupled with vision agent loopback scripts to generate wireframes dynamically.

Agent abstraction layers coordinating multi-modal image edits, composition layouts, and structural inpainting tasks.

Control mechanisms giving media-focused agents structural interfaces to toggle art installations, DMX lights, and live MIDI events.

Equips Ollama models with coordinated tool definitions to execute localized object-detection and cropping pipelines.

Interface monitoring tools tracking processing updates across nested multi-modal asset creation pipelines visually.

AlignDev helps AI-assisted frontend teams generate shared coding standards and SKILL.md so Claude Code, Codex, Cursor, Copilot, and other agents write consistently.

通用 AI 生图 skill：原样传递用户提示词，统一调用多种生图接口，并自动匹配常见平台图片尺寸。

🪧 Claude Code / Codex skill — generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial × Swiss visual systems, 28 layouts, 10 themes, single-file HTML → PNG. 小红书图文 + 公众号封面对

v3.5 — 五护盾+接口解耦+SOM锚点引擎。Win32/WinUI3/Electron/Qt全覆盖桌面GUI操控skill。

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.