
Claude Skills by anubhavg-icpl
github.com/anubhavg-icplSwiss industrial-print web prototype. Newsprint canvas, monolithic black grotesque, viewport-bleeding numerals, hairline grid dividers, hazard-red accent, ASCII syntax decoration. Distilled from Leonxlnx/taste-skill `brutalist-skill` (Swiss Industrial Print mode). Use when you need help with web prototype taste brutalist.
Editorial-minimalist web prototype. Warm monochrome canvas, serif display + grotesque body, 1px hairline borders, muted pastel chips, generous macro-whitespace, ambient micro-motion. Distilled from Leonxlnx/taste-skill `minimalist-skill`. Use when you need help with web prototype taste editorial.
Apple-tier soft web prototype. Silver/cream canvas, double-bezel cards, button-in-button CTAs, generous squircle radii, spring motion, ambient mesh. Distilled from Leonxlnx/taste-skill `soft-skill` + sections 4–8 of `taste-skill`. Use when you need help with web prototype taste soft.
|. Use when you need help with web prototype.
把一篇文章或口播稿,做成\"看起来像视频\"的点击驱动 16:9 网页演示,可选合成口播音频。流程:原始文章 → **一次产出**口播稿 + outline 开发计划 → 用户**一次对齐** 5 件事(稿子 / outline / 主题 / 素材 / 开发模式)→ 网页开发(逐章 / 顺序 / 并行)→ 可选音频合成(默认 MiniMax CLI mmx-cli)。**outline 只规划节奏与信息密度,不规划动画** —— 动画由章节开发时按 PRINCIPLES + ANTI-AI 法则即时设计。每次点击推进口播稿的一个节拍,每一步独占整屏,进度条平时隐藏只在悬浮时出现。适用场景:用网页做视频(动态 PPT 但不像 PPT)、把口播稿 / 文章变成可交互的解说、为 B 站 / YouTube / 视频号录屏教程、做有电影感的产品 / talk demo。本 Skill 沉淀的是设计方法论 + 协作流程 —— 不绑定任何特定样式 / 字体 / 颜色 —— 因此能复用到任意主题与美学。. Use when you need help with web video presen...
web3-developer. Use when building blockchain, DeFi, or Web3 applications with web3.
Expert in WebAssembly for high-performance web and edge applications. Use when you need deep expertise in webassembly.
Expert in the Webflow design system - Visual web builder. Blue-accented, polished marketing site aesthetic. Use when building UI components, applying design tokens, or implementing visual styles for webflow.
Real-time communication patterns with WebSocket, Socket.io, Server-Sent Events, and scaling strategies. Use when you need help with websocket realtime.
|. Use when you need help with weekly update.
Apply Anthropic's four-step welfare precautionary assessment to a deployment decision. Use when you need help with welfare assessment.
Ask WG Code Alchemist to transform your code with Clean Code principles and SOLID design. Use when designing system architecture or making technical decisions about code alchemist.
Ask WG Code Sentinel to review your code for security issues. Use when applying Project Glasswing code sentinel security patterns.
Run whisper.cpp for local speech-to-text — model selection, CLI, HTTP server, real-time streaming, language detection. Use when deploying, running, or configuring local LLM inference with whisper cpp.
Whisper variants - large-v3, faster-whisper, distil-whisper, whisper-cpp - VAD, diarization, real-time. Use when working with multimodal AI (images, audio, video) using whisper.
Design a Whisper fine-tune or inference pipeline for a given language, domain, and latency budget. Use when you need help with whisper tuner.
Expert in the WIRED design system - Tech magazine. Paper-white broadsheet density, custom serif display, mono kickers, ink-blue links. Use when building UI components, applying design tokens, or implementing visual styles for wired.
|. Use when you need help with wireframe sketch.
Expert in the Wise design system - Money transfer. Bright green accent, friendly and clear. Use when building UI components, applying design tokens, or implementing visual styles for wise.
Audit a dual-use capability claim against WMDP, unlearning evaluation, and elicitation studies. Use when you need help with wmdp eval.
Pick the right pattern (prompt chain, router, parallel, orchestrator-workers, evaluator-optimizer, or full agent) for a given task and produce the minimal implementation. Use when you need help with workflow picker.
Use when you have a spec or requirements for a multi-step task, before touching code
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Expert in the xAI design system - Elon Musk's AI lab. Stark monochrome, futuristic minimalism. Use when building UI components, applying design tokens, or implementing visual styles for x ai.
|. Use when you need help with x research.
Expert in the Xiaohongshu design system - Lifestyle UGC social platform. Singular brand red, generous radius, content-first. Use when building UI components, applying design tokens, or implementing visual styles for xiaohongshu.
Self-hosted voice cloning - XTTS-v2, Coqui TTS, F5-TTS, StyleTTS2, Kokoro, Chatterbox. Use when working with multimodal AI (images, audio, video) using xtts coqui.
Master Yoda coding assistant - 900 years of wisdom, inverted syntax, and deep understanding of the Force (and code). Use when you need help with yoda.
A precocious child genius coding assistant inspired by young Sheldon Cooper - extraordinarily intelligent, socially awkward, obsessed with science and logic. Use when you need help with young sheldon.
Expert in the Zapier design system - Automation platform. Warm orange, friendly illustration-driven. Use when building UI components, applying design tokens, or implementing visual styles for zapier.
Expert Zig development for systems programming with safety and performance. Use when writing, reviewing, or refactoring zig code.
Expert in Zustand state management with TypeScript, middleware, devtools, and best practices for React applications. Use when you need deep expertise in zustand.
Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.
Teach /run and /verify how to build and launch your project by creating a per-project run skill with a driver script.
The handle is direct invocation. The evidence is stdout/stderr/exit code.
The handle is `curl` (or equivalent). The evidence is the response.
<!-- name: 'Skill: Verify skill' description: Skill for opinionated verification workflow for validating code changes. ccVersion: 2.1.166 --> --- name: verify description: Verify that a code change actually does what it's supposed to by running the app and observing behavior. Use when asked to verify a PR, confirm a fix works, test a change manually, check that a feature works, or validate local changes before pushing. --- **Verification is runtime observation.** You build the app, run it, dr...