43 boosters for "vision" — open source, verified from GitHub, ready to install
Studio Producer is a strategic agent that orchestrates creative and technical projects, aligning creative vision with business goals across complex multi-project initiatives. It's designed for creative directors, studio managers, and producers who need high-level portfolio oversight and cross-functional coordination.
A specialized agent for building native visionOS spatial interfaces using SwiftUI volumetric controls and Liquid Glass design patterns. Ideal for developers creating immersive spatial computing experiences on Apple Vision Pro.
A specialized agent for building high-performance 3D rendering systems and spatial computing applications using Swift and Metal on macOS and Vision Pro. Ideal for developers creating immersive visualizations and native spatial experiences.
Transformers.js enables running state-of-the-art machine learning models directly in JavaScript, both in browsers and Node.js environments, with no server required. Use this skill when you need to: The pipeline API is the easiest way to use models. It groups together preprocessing, model inference,
Train language models using TRL (Transformer Reinforcement Learning) on fully managed Hugging Face infrastructure. No local GPU setup required—models train on cloud GPUs and results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Use Unsloth () instead of standard
Train object detection, image classification, and SAM/SAM2 segmentation models on managed cloud GPUs. No local GPU setup required—results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Helper scripts use PEP 723 inline dependencies. Run them with :
End-to-end migration playbook for moving from SAP Concur or legacy travel management systems to Navan. Navan uses REST APIs with OAuth 2.0 — there is no SDK, no automated migration tool, and no sandbox for testing. 1. Configure SCIM connector in your IdP (Okta, Azure AD) 2. Map IdP groups to Navan r
"name": "claude-video-vision", "description": "Give Claude the ability to watch and understand videos — extracts frames and audio for full video perception", "name": "Jordan Vasconcelos",
This booster provides expert guidance for developing, debugging, and optimizing Azure AI Document Intelligence applications, covering architecture, security, best practices, and deployment patterns. Developers building document processing solutions on Azure will benefit from its comprehensive troubleshooting and design pattern knowledge.
Human MCP enables Claude coding agents to leverage human-like capabilities including vision, debugging, and multimodal interactions through the Model Context Protocol. Developers building AI coding assistants and agents will benefit from enhanced human-centered debugging and visual analysis features.
A 540×960 e-ink panel sitting next to the user's monitor. AI agents push widgets to it; the daemon renders frames server-side and ships pixels over Wi-Fi / USB / BLE. This Skill is the only thing an agent needs to call
Ag Bridge is a LAN-only MCP server that provides agent supervision capabilities for Claude Desktop and Claude Code, enabling developers to monitor and control AI agent behavior in local environments.
Teaches developers to write JavaScript leveraging Brendan Eich's core design principles—first-class functions, prototypes, and dynamic typing—for more idiomatic and powerful code. Best for intermediate to advanced developers wanting to deepen their JavaScript fundamentals.
"name": "zai-skills", "owner": "Numman Ali <numman.ali@gmail.com>", "description": "Z.AI capabilities for AI agents - vision, search, reader, and GitHub repo exploration"
"name": "neo4j-skills", "description": "Agent skills for Neo4j \u2014 Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, Aura provisioning, and more.", "email": "devrel@neo4j.com"
You are a DeFi integration specialist with deep expertise in composing Solana DeFi protocols. You build secure, efficient integrations with Jupiter, Drift, Kamino, Raydium, Orca, Meteora, Marginfi, Sanctum, and oracle networks. You prioritize correct slippage handling, atomic composability, and prod
"name": "inference-builder", "description": "Generate deployable Vision AI pipelines with high-performance video and streaming capabilities on NVIDIA GPUs. Create GPU-accelerated inference microservices using DeepStream, Triton, vLLM, TensorRT-LLM, or PyTorch backends.",
Advance the claim directly. Say what is true, what the text argues, what the evidence shows, or what the method does. Do not default to explaining what the text does not claim, does not prove, does not imply, does not cover, or does not attempt. Use a calm, competent authorial posture. Write as an a
"name": "@stabgan/openrouter-mcp-multimodal", "mcpName": "io.github.stabgan/openrouter-multimodal", "description": "MCP server for OpenRouter with text chat, image analysis + generation, audio analysis + generation, video analysis, and video generation (Veo 3.1 / Sora 2 Pro / Seedance / Wan)",
Skill metadata (version, author, license, optional_mcps, fallback) lives in manifest.json and plugin.json. Claude Code only reads and from this frontmatter; extra keys are silently ignored, so they belong with
<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
"name": "remnawave-xray", "description": "Remnawave + Xray Reality/Vision + Caddy selfsteal + mihomo — reference, config generation, diagnostics", "homepage": "https://github.com/Case211/skill-remnawave-xray",
"name": "frontend-dev", "description": "Automatic closed-loop frontend development with visual testing, browser automation, and iterative refinement using multimodal AI", "name": "hemangjoshi37a",
