Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
websocket-patterns
WebSocketによる双方向リアルタイム通信パターン専門スキル。
接続ライフサイクル管理、メッセージキューイング、ハートビート戦略、エラーリカバリーを提供する。
Anchors:
• RFC 6455 (WebSocket Protocol) / 適用: プロトコル仕様 / 目的: 標準準拠の実装
• 『Designing Data-Intensive Applications』(Martin Kleppmann) / 適用: メッセージング設計 / 目的: 信頼性確保
• Circuit Breaker Pattern / 適用: エラーリカバリー / 目的: 障害伝播防止
Trigger:
Use when implementing WebSocket connections, real-time bidirectional communication, connection lifecycle management, message queueing, or heartbeat monitoring.
majiayu000/claude-skill-registry 163
-
project-estimation
Estimate project scope, timeline, and resource requirements using multiple estimation techniques including bottom-up, top-down, and analogous estimation methods for accurate project planning.
majiayu000/claude-skill-registry 163
-
mlops-dag-builder
Design DAG-based MLOps pipeline architectures with Airflow, Dagster, Kubeflow, or Prefect. Activates for DAG orchestration, workflow automation, pipeline design patterns, CI/CD for ML. Use for platform-agnostic MLOps infrastructure - NOT for SpecWeave increment-based ML (use ml-pipeline-orchestrator instead).
majiayu000/claude-skill-registry 163
-
develop-frontend
Next.js/Reactによるフロントエンド実装スキル（UI、API連携、状態管理、テスト）
majiayu000/claude-skill-registry 163
-
ai-board
Advanced multi-agent reasoning system for complex questions requiring maximum accuracy. Uses adaptive technique selection, adversarial validation, multi-agent debate, and deep analysis. Trigger phrases "ai board", "expert panel", "deep analysis", "maximum accuracy", "thorough reasoning". Use for critical medical decisions, theological questions, philosophical analysis, complex technical problems, high-stakes decisions, or any question requiring 95%+ confidence.
majiayu000/claude-skill-registry 163
-
validating-architecture-analysis
Validate architecture artifacts against contracts and consistency requirements - codifies systematic validation practices with professional reporting
majiayu000/claude-skill-registry 163
-
scientific-workflows
Expert assistant for choosing and implementing scientific workflow tools - from simple joblib caching to complex orchestration with Prefect, Parsl, FireWorks, and quacc. Recommends the simplest solution that meets requirements.
majiayu000/claude-skill-registry 163
-
vote-reset
Generate Safe UI compatible multisig batch JSON to reset veNFT votes. Use when the user wants to reset votes, clear voted status, or prepare vote reset transactions for a multisig wallet.
majiayu000/claude-skill-registry 163
-
recruitment-source-finder
This skill should be used when users need to find relevant sources from the sources.md knowledge base for recruitment-related topics. Parses and filters the comprehensive sources.md file to return targeted sub-lists of resources based on topic queries, making research more efficient.
majiayu000/claude-skill-registry 163
-
oss:issue-discovery
Phase 1 of OSS contribution - Find and evaluate suitable issues matching your skills, time, and learning goals. Filters by labels, assesses project health, and provides structured recommendations. Use when starting OSS contribution, looking for beginner-friendly issues, or evaluating multiple issue options.
majiayu000/claude-skill-registry 163
-
nano-banana-assets
Generate any kind of visual asset using OpenRouter's Nano Banana Pro (Google Gemini 3 Pro Image Preview). Handles images, graphics, illustrations, icons, banners, backgrounds, UI elements, stickers, characters, and more. Flexible and adaptable to any creative request.
majiayu000/claude-skill-registry 163
-
agent-workflow
Multi-agent development workflow system. Load when orchestrating development tasks, spawning subagents, or managing workflow phases.
majiayu000/claude-skill-registry 163
-
risk-sizing-not-blocking
Risk managers should SIZE trades, not BLOCK them. Trigger when: (1) capital manager blocks trades, (2) risk manager rejects orders, (3) trades fail due to 'exceeds limit', (4) components don't work in harmony.
majiayu000/claude-skill-registry 163
-
a2ui-v0-8
使用 A2UI v0.8（以 renderers/lit/src/0.8 与 specification/0.8 为准）生成服务端 JSONL UI 消息，并实现客户端事件与 A2A 扩展回传。适用于把用户需求转成 A2UI 组件树+数据模型+渲染序列，以及处理 action/userAction 与后端接口调用的场景。
majiayu000/claude-skill-registry 163
-
lumen-dashboards
Master declarative, no-code data dashboards with Lumen YAML specifications. Use this skill when building standard data exploration dashboards, connecting multiple data sources (files, databases, APIs), creating interactive filters and cross-filtering, designing responsive layouts with indicators and charts, or enabling rapid dashboard prototyping without writing code.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-sandbox-list
List sandboxes with optional filtering. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
component-library
Build production-grade, accessible, and tested component libraries with Storybook, Chromatic, and design tokens
majiayu000/claude-skill-registry 163
-
web-ui-analysis
Analyze web interfaces for UX issues, accessibility compliance (WCAG 2.1), color contrast, typography hierarchy, responsive design, and Core Web Vitals. Returns actionable improvements with code examples.
majiayu000/claude-skill-registry 163
-
ffmpeg
Guide for using FFmpeg - a comprehensive multimedia framework for video/audio encoding, conversion, streaming, and filtering. Use when processing media files, converting formats, extracting audio, creating streams, applying filters, or optimizing video/audio quality.
majiayu000/claude-skill-registry 163
-
state-lifting
Reactにおける状態リフティングと状態配置判断を支援するスキル。
兄弟コンポーネント間の状態共有、Prop Drilling削減、Context導入判断、
Compound Componentパターンまで、React状態管理の全体像を扱う。
Anchors:
• React Documentation (Lifting State Up) / 適用: 共有状態の配置判断 / 目的: 最小責務での共有設計
• Thinking in React / 適用: 状態配置の判断フロー / 目的: 最適な状態配置の特定
• Kent C. Dodds (Colocation) / 適用: 状態と利用箇所の距離 / 目的: 保守性とパフォーマンスの両立
Trigger:
Use when lifting state between components, sharing state across siblings, reducing prop drilling, deciding on Context usage, or implementing compound components.
state lifting, prop drilling, context api, state placement, compound component, react state, colocation
majiayu000/claude-skill-registry 163
-
vuejs
Expert knowledge for working with VueJS, the preferred frontend framework we use along with Vite as a bundler
majiayu000/claude-skill-registry 163
-
mental-models
Apply Charlie Munger's latticework of mental models to any problem. Use when user requests decision analysis, says "help me think", "apply mental model", mentions model names (inversion, bottlenecks, second-order thinking), or needs structured thinking frameworks.
majiayu000/claude-skill-registry 163
-
i18n-setup-wizard
Sets up complete internationalization infrastructure for React, Vue, Next.js, or vanilla JS with framework config, translation files, and language switching. Use when user asks to "setup i18n", "add translations", "multi-language support", or "internationalization setup".
majiayu000/claude-skill-registry 163
-
testing-visual-regression
Detect visual changes in UI components using screenshot comparison.
Use when detecting unintended UI changes or pixel differences.
Trigger with phrases like "test visual changes", "compare screenshots", or "detect UI regressions".
majiayu000/claude-skill-registry 163