LLM 與 Agent

Connect Supabase databases to Claude Desktop artifacts with authentication and read-only queries using native fetch API.

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

Automatically sync the documentation structure from docs/content/{en,uk}/ to CLAUDE.md when changes are detected in the docs directory. This skill should be triggered when documentation files are added, removed, or reorganized, or when explicitly requested by the user or agents.

Complete guide for OpenAI's traditional/stateless APIs: Chat Completions (GPT-5, GPT-4o), Embeddings,Images (DALL-E 3), Audio (Whisper + TTS), and Moderation. Includes both Node.js SDK and fetch-basedapproaches for maximum compatibility.Use when: integrating OpenAI APIs, implementing chat completions with GPT-5/GPT-4o, generating textwith streaming, using function calling/tools, creating structured outputs with JSON schemas,implementing embeddings for RAG, generating images with DALL-E 3, transcribing audio with Whisper,synthesizing speech with TTS, moderating content, deploying to Cloudflare Workers, or encounteringerrors like rate limits (429), invalid API keys (401), function calling failures, streaming parseerrors, embeddings dimension mismatches, or token limit exceeded.Keywords: openai api, chat completions, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4o, gpt-4-turbo,openai sdk, openai streaming, function calling, structured output, json schema, openai embeddings,text-embedding-3, dall-e-3, image ge

Use when setting up a new dev machine for Claude Code, onboarding to a project, or optimizing development environment - interactive installer that detects existing setup, configures shell, editor, git, templates, and quality gates with configurable enforcement

Comprehensive context engineering and prompt patterns for AI agents. Covers code review, financial systems, KPI systems, data integration MVP, and modern best practices. Based on 2025 research from Anthropic, LangChain, and industry leaders.

Master MongoDB schema design and data modeling patterns. Learn embedding vs referencing, relationships, normalization, and schema evolution. Use when designing databases, normalizing data, or optimizing queries.

Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel

Create a new Claude Code plugin with proper directory structure and manifest. Use when the user wants to create a new plugin from scratch. Sets up plugin.json, directory structure, and optional components.

Framework for delegating tasks to external LLM services, with a focus on strategic oversight and quality control.

ReviewAgent スキル - コード品質判定・静的解析・セキュリティスキャン・品質スコアリング。生成されたコードに対して100点満点で品質評価し、80点以上で合格判定。Use when:- コード品質をレビューする時- 静的解析（ESLint、TypeScript）が必要な時- セキュリティスキャンが必要な時- 品質スコアを算出する時- "レビュー", "品質チェック", "セキュリティ", "スキャン" がキーワードに含まれる時

This skill should be used when the user asks about "CLAUDE.md structure", "settings.json format", "category optimization", "self-improvement", "Main Agent configuration", "category maintenance", "improvement cycle", or needs guidance on optimizing Claude Code categories. Provides patterns for CLAUDE.md, settings.json, and self-improvement workflows.

Checkpoint framework and validation rules for all agents. Ensures quality gates are passed at every stage of development.

Query multiple AI agents in parallel for diverse perspectives. Use when you want multiple viewpoints on a question, to compare approaches, or to find consensus among AI models.

Expert test writing including unit, integration, e2e tests, mocking, and coverage strategies

GitHub Copilotカスタマイゼーションファイル（プロンプト、エージェント、インストラクション、スキル）の作成ガイド。.prompt.md、.agent.md、.instructions.md、SKILL.mdファイルをVS Codeのベストプラクティスに従って作成する際に使用してください。

Repository onboarding and agent bootstrap. Use at the start of a new repo session or before any task to load AGENTS.md, architecture/skills indexes, and discover local Codex skills.

.claude/skills/以下に新しいスキルを作成するためのガイドとテンプレートを提供します。スキルの目的、アクティベーション条件、チェックリスト、詳細なリファレンス、例、テンプレートの作成を支援します。

Agent with selective Gemini safety settings for specific categories

Intelligent financial management skill for Claude Code that provides comprehensive PocketSmith API integration with AI-powered analysis, transaction categorization, rule management, tax intelligence, and scenario planning. Use when working with PocketSmith data for (1) Transaction categorization and rule management, (2) Financial analysis and reporting, (3) Australian tax compliance (ATO) and deduction tracking, (4) Scenario analysis and forecasting, (5) PocketSmith setup health checks, (6) Budget optimization and spending insights.