LLM 與 Agent

Set up AI tool symlinks in a repository for multi-agent compatibility. Use when the user wants to set up skills for Gemini, Claude, or other AI tools, or when they mention "setup skills", "configure agents", or "link AGENTS.md".

Expert prompt optimization specialist that helps users craft, refine, and optimize prompts for Claude API to maximize effectiveness, reduce token usage, and improve output quality

Claude Code plugin structure and requirements. Use when creating, validating, or troubleshooting plugins. Covers plugin.json schema, SKILL.md format, command frontmatter, and agent configuration.

Generate effective prompts based on task descriptions. Use when you need to create structured prompts for AI models.

Maximizing Claude Code capabilities and efficiency.Use when helping users discover features, optimize workflows, or improve their Claude Code experience.

Implement a StarCraft 2 / RTS-inspired "God Mode" command interface for orchestrating autonomous systems. Use this skill when building dashboards for AI orchestration, multi-agent systems, autonomous manufacturing, robotics control, or any interface requiring real-time monitoring of multiple resources/units with command-and-control capabilities. Includes D3.js global network map for visualizing and onboarding distributed printer fleets. Applies to React 19 + TypeScript + Vite projects targeting dark sci-fi aesthetics with resource bars, minimaps, command panels, event logs, and geographic site selection.

Apply MAKER (Massively Decomposed Agentic Processes) to solve long sequential tasks using task decomposition, multi-agent voting, and error correction. Use when facing complex multi-step problems, sequential planning, constraint satisfaction, or tasks requiring many consecutive decisions.

LlamaIndex implementation patterns with templates, scripts, and examples for building RAG applications. Use when implementing LlamaIndex, building RAG pipelines, creating vector indices, setting up query engines, implementing chat engines, integrating LlamaCloud, or when user mentions LlamaIndex, RAG, VectorStoreIndex, document indexing, semantic search, or question answering systems.

Guide users through creating, reviewing, and editing Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.

Autonomous patent examination agent. Simulates USPTO examination by analyzing applications for compliance with 35 U.S.C. §§ 101, 102, 103, 112 and identifying potential office action issues.

Use when creating or editing agent definitions - ensures proper frontmatter, clear structure, validation of references, and no duplication with existing agents

Export Claude skills. Use to generate documentation of all available Claude Skills.

Always use this skill at the start of a task to check whether relevant information already exists. Use when users ask to recall, search memories, or subscribe to updates. Triggers on "recall", "search memories", "list keys", "share", "subscribe to", or any persistent storage request.

Validates code against Home Assistant Custom Card requirements and the project's strict architecture rules. Use this before finalizing any Phase 1 or Phase 2 task.

Comprehensive testing and validation tools for Clerk authentication integrations. Includes E2E auth flow testing, security audits, configuration validation, unit testing patterns for sign-in/sign-up flows. Use when implementing Clerk tests, validating authentication setup, testing auth flows, running security audits, creating E2E tests for Clerk, or when user mentions Clerk testing, auth validation, E2E authentication tests, security audit, or test coverage.

Create new Claude Code agent skills. Automatically analyzes requirements and generates complete skill with proper structure, triggers, and tools. Use when you want to "create a skill", "build a new skill", "make a skill for", or automate repetitive tasks.

Executes tests, analyzes test results, checks test coverage, and provides comprehensive testing status overview. Primarily for Go projects. Activates after implementing/modifying code to verify correctness, or when explicitly requested to assess test suite health.

Solve context fragmentation across Claude sessions. Use when users mention re-explaining themselves, losing conversation context, starting over, "you forgot," context loss, session continuity, picking up where we left off, or wanting Claude to remember across chats. Also use when users want to create/update their passport, generate session summaries, or maintain project continuity.

This skill provides comprehensive knowledge for working with the Anthropic Messages API (Claude API). It should be used when integrating Claude models into applications, implementing streaming responses, enabling prompt caching for cost savings, adding tool use (function calling), processing images with vision capabilities, or using extended thinking mode.Use when building chatbots, AI assistants, content generation tools, or any application requiring Claude's language understanding. Covers both server-side implementations (Node.js, Cloudflare Workers, Next.js) and direct API access.Keywords: claude api, anthropic api, messages api, @anthropic-ai/sdk, claude streaming, prompt caching, tool use, vision, extended thinking, claude 3.5 sonnet, claude 3.7 sonnet, claude sonnet 4, function calling, SSE, rate limits, 429 errors

SpecWorkflowMcpとAI連携による仕様駆動開発(SDD)完全自動化スキル。 PRD→SPEC→実装タスク→品質検証→Miyabi連携までを1コマンドで完結。 kiroやspec-flowの考え方を統合し、Claude Sonnet 4による高品質な仕様生成とタスク分解を実現。 あらゆるソフトウェア開発プロジェクトに適用可能な汎用SDDプラットフォーム。