LLM & Agents

Customize ChatKit layout, theme, and presentation for RAG textbook chatbot with proper styling and textbook theme integration.

Implement S3 operations with rust-s3 including streaming downloads, multipart uploads, and batch operations. Use for cloud storage integration.

Official ollama Python library for LLM inference. Provides a clean,Pythonic interface for text generation, chat completion, embeddings,model management, and streaming responses.

Create new Agent Skills with proper structure, templates, and best practices. Use when building custom skills for Claude Code, GitHub Copilot, or other Agent Skills-compatible tools.

Design and implement the Viet K-Connect document generation template engine (DB-driven wizard schema + PDF renderSpec + history + Storage upload). Start with 2 templates and scale linearly to 50 without hardcoding.

Create, optimize, and debug high-performing prompts for Claude 4 models with production-ready templates and evidence-based techniques. Use this skill when the user asks to create a prompt, write a prompt, improve a prompt, build a prompt chain, design a system prompt, or needs prompt engineering guidance. Also handles prompt refinement and follow-up modifications.

Use when writing pytest tests, creating fixtures, mocking dependencies, or testing async code - provides patterns that verify actual behavior with proper fixtures and parametrization; prevents testing mocks instead of code (plugin:python@dot-claude)

MCP Gateway design patterns for Agent Gateway, Subprocess, and Daemon isolation. Use when designing MCP integrations.

UI/UX design for digital board games. Use when building game interfaces, implementing drag-and-drop, rendering game boards, showing player information, handling animations, or designing responsive layouts. Covers Canvas, SVG, and DOM-based approaches.

Multi-provider website scraper that converts any website (including CSR/SPA) to deployable static sites. Uses Playwright, Apify RAG Browser, Crawl4AI, and Firecrawl for comprehensive scraping. Triggers on requests to clone, reverse-engineer, or convert websites.

Comprehensive Next.js project setup from scratch following industry best practices. Use when creating new Next.js projects, requiring template selection, design system ideation, specifications, wireframes, implementation with TDD, QA validation, and complete documentation. Handles both simple quick-start and complex multi-phase projects with sub-agent orchestration.

Install agent skills from GitHub repositories into local environment. Pure agentic installation - no scripts required. Use when adding new skills or updating existing ones.

This skill provides reusable implementation patterns extracted from the better-chatbot project for custom AI chatbot deployments. Use this skill when building AI chatbots with server action validators, tool abstraction systems, workflow execution, or multi-AI provider integration in your own projects (not contributing to better-chatbot itself).Use when: building AI chatbot features, implementing server action validators, creating tool abstraction layers, setting up multi-AI provider support, building workflow execution systems, adapting better-chatbot patterns to custom projectsKeywords: AI chatbot patterns, server action validators, tool abstraction, multi-AI providers, workflow execution, MCP integration, validated actions, tool type checking, Vercel AI SDK patterns, chatbot architecture

Use when validating or creating Claude Code component names - naming conventions with kebab-case patterns, reserved words, and length limits for November 2025 specifications

Map and navigate relationships between Claude skills.

Create new Claude skills following Anthropic best practices. Use when building specialized agent capabilities, packaging procedural knowledge, or extending Claude's domain expertise.

Generate adversarial inputs, edge cases, and boundary test payloads for stress-testing LLM robustness

Master skill for Wolf Agents institutional knowledge and behavioral patterns (v1.1.0 with skill-chaining)

仕様を実行可能テスト（verify.md）に変換し、カバレッジを分析するワークフロー。Runme.dev形式でE2E/統合テストを記述。使用タイミング:(1) 仕様書（spec.md等）から実行可能なテストドキュメントを作成したい場合(2) テストカバレッジを分析・可視化したい場合(3) 「verify.md作成」「カバレッジチェック」「テスト文書化」リクエスト使用しない場合: ユニットテストのみ必要な場合、既存テストフレームワークで十分な場合

Transform any intellectual work into AI-promptable systems. Use when user wants to automate business processes, create multi-agent workflows, decompose complex work into AI-delegatable tasks, or build frameworks for recurring intellectual work (competitive analysis, strategic planning, BMC, OKRs, reports, etc.). Applies to work with clear inputs, context, and expected outputs.