MCP App StoreMCP App Store
from pixijs-skills84
Guides an agent to load, manage, and cache textures, videos, spritesheets, fonts, and other assets using PixiJS v8's Assets API, including bundles, manifests, b
Provides a complete reference and procedural guide for using PixiJS v8's Assets API to load, resolve, cache, and unload resources (textures, spritesheets, video textures, web/bitmap fonts, GIFs, compressed textures, SVGs, and JSON). Includes quick-start examples, supported file types, parser forcing for extension-less URLs, recommended runtime init options, load options and per-asset data, progress and error-handling patterns, and common pitfalls (e.g., Texture.from vs Assets.load, unloading between levels).
Use this skill whenever an agent needs to load or manage media and game assets in PixiJS v8: single-image loads, grouped bundles per level/scene, manifest-driven preloads, background priming of next-level assets, or when working with signed/CDN/extension-less URLs that require explicit parser selection. Also useful for performance-sensitive flows that need GPU memory management or compressed texture handling.
has_scripts=false).parser, LoadOptions and data shapes, and a decision guide for common workflows.Best suited for coding agents with JS/TypeScript and PixiJS familiarity (Copilot-style or Codex-like agents, Cursor/GitHub Copilot environments). Agents that can run or propose TypeScript snippets will benefit most.
PixiJS Assets v8 skill — pure documentation skill with no bundled scripts. Covers the full Assets API: init, load/unload, bundles, manifests, background loading, progress, caching, spritesheets, video textures, fonts, GIFs, compressed textures, SVG. Exceptionally well-written with clear code examples, a decision guide, common mistakes section, and 12 reference sub-documents for progressive disclosure.
No scripts to audit — static analysis only. SKILL.md is high quality: specific triggers, comprehensive coverage, well-structured. Minor dock on security for external links in markdown (theoretical risk only). Architecture is strong with clear reference-based progressive disclosure pattern.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Algolia Cost Tuning
Practical guide to reduce Algolia billing by auditing records/requests, switching to virtual replicas, multi-query usage, caching, and cleanup strategies.
FFmpeg Guide
Comprehensive FFmpeg reference for encoding, converting, streaming, filtering, and analyzing audio/video — command examples, common patterns, and troubleshootin
Provide Raw YouTube Video ID
Return only a valid existing YouTube video ID string (no URL, no commentary) — useful for tools that need raw IDs for downstream operations.
samber/hot — In-memory Caching for Go
Guidance and patterns for using samber/hot in Go: eviction algorithms, TTL, loaders, sharding, stale-while-revalidate, and Prometheus monitoring.
Narrator AI CLI
CLI client to create AI-narrated videos: writing, clip generation, composing and visual templates with 90+ narration styles, 146 BGM tracks and 63 dubbing voice
Image to 3D Pipeline
Convert 2D images into optimized, rigged 3D models (GLB/FBX) and animations using Hunyuan3D, Mixamo and cleanup tools — fast pipeline for web and game assets.
Turborepo Guidance
Practical Turborepo guidance for JavaScript/TypeScript monorepos: task configuration, caching, filtering, and CI best-practices.