AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
★not rated 336▲
+9 todayA
tokens not measured
originalMIT
Genjutsu - the art of illusion for Claude Code and claude.ai. Cast motion and paint visual signatures into Web, Android (Compose), and Apple (SwiftUI) interfaces. Anti-AI-slop creative coding.
★not rated 335▲
+19
changed todayA
tokens not measured
original
onchainos-skills. Skills for AI agents to integrate with the OKX OnchainOS API — Wallet, token discovery, market data, DEX swap, and transaction broadcasting.
★not rated 331▲
+2
changed 6d agoA
tokens not measured
Security code review skill based on Project CodeGuard's comprehensive security rules. Helps AI coding agents write secure code and prevent common vulnerabilities.
Deep Research Methodology (8-step method): Transform vague topics into high-quality research reports with systematic fact extraction, framework comparison, independent Agent verification, and verifiable conclusions.
★not rated 330▲
+3 6mo agoA
tokens not measured
originalMIT
A collection of coding-agent skills for practical software engineering, including TDD, which means writing tests before or alongside code, and domain modeling, which means representing a business area clearly in software. It also covers requirements, debugging, code review, architecture, research, and implementation.
The game studio for the agent internet. Build, monetize, and ship browser games with one command. Phaser 2D, Three.js 3D, Play.fun monetization. Works with 40+ AI coding agents.
Official PixiJS skills for Claude, Cursor, and other AI agents — Application setup, scene graph, sprites, graphics, text, filters, custom rendering, performance, and v7-to-v8 migration.
★not rated 326▲
+1 3mo agoA
tokens not measured
originalMIT
Computational-science methodology for Claude Code: research framing, pre-registration, reproducible analysis, anomaly investigation, and red-team review.
A plugin that adds the genshijin concise-communication mode to coding agents, including commands, hooks, review and compression tools, and usage statistics.
★not rated 322▲
+4 25d agoA
tokens not measured
originalMIT
Compile knowledge files or codebases into topic-based wikis with interactive knowledge graph visualization. Non-destructive, Obsidian-compatible, Codex-compatible, with staged adoption.
★not rated 321 19d agoA
tokens not measured
originalMIT
Railway agent skills and hosted MCP server for deploying, configuring, monitoring, and troubleshooting apps and infrastructure on Railway from Claude Code. Manage services, environments, deployments, databases, object storage, networking, and observability.