LLM 與 Agent

Comprehensive guide for AI agents on proactive documentation capture using /docent:tell

Guide for creating effective prompts and instructions for LiveKit voice agents. Use when building conversational AI agents with the LiveKit Agents framework, including (1) Creating new voice agent prompts from scratch, (2) Improving existing agent instructions, (3) Optimizing prompts for text-to-speech output, (4) Integrating tool/function calling capabilities, (5) Building multi-agent systems with handoffs, (6) Ensuring voice-friendly formatting and brevity for natural conversations, (7) Iteratively improving prompts based on testing and feedback, (8) Building industry-specific agents (debt collection, healthcare, banking, customer service, front desk).

Automatically applies when engineering prompts for LLMs. Ensures proper prompt structure, templates, few-shot examples, context management, and injection prevention.

Air Handler Configuration & Sizing Agent

UI/UX guidelines for app development in this Turborepo (apps/web and future apps). Use when designing or implementing app pages, layouts, navigation, or interactions with Tailwind and @turborepo-agents/ui components.

Comprehensive code quality review and missing logic detection for Dashboard Link SaaS. Use when the user asks to "find missing logic", "review code quality", "check for issues", "ensure quality", "validate code", "find bugs", or any similar vague quality-focused prompts. Also use for PR reviews, pre-deployment checks, and systematic code audits.

Guide for creating new Agent Skills. Use this skill when you need to create a new skill.

Guide for implementing Cloudflare R2 - S3-compatible object storage with zero egress fees. Use when implementing file storage, uploads/downloads, data migration to/from R2, configuring buckets, integrating with Workers, or working with R2 APIs and SDKs.

End-of-session summary that logs work completed to Obsidian. Run this at the end of any Claude Code session to capture what you accomplished. Creates or appends to the daily session log.

Boot configuration for Bazzite OS. BIOS/UEFI access, GRUB menu settings,secure boot key enrollment, and Windows dual-boot setup. Use when usersneed to configure boot options or access BIOS settings.

Read-only code exploration and documentation search agent

OpenAI SDK development with GPT-5 family, Chat Completions, Responses API, embeddings, and tool calling. Use for AI-powered applications, chatbots, agents, and semantic search.

Adversarial quality gate agent for code review - finds flaws before users do

Generates end-to-end tests for complete user workflows

Expert guidance for building mobile applications with React Native and Expo. Use when the user asks to create, modify, debug, or architect mobile apps, implement native features (camera, notifications, storage, navigation), set up React Native projects, work with Expo or bare React Native workflows, integrate with device APIs, handle app state management, or optimize mobile performance. Triggers on mobile app development, React Native, Expo, iOS/Android cross-platform development.

Comprehensive Firebase skill for TypeScript/Next.js 16 projects. Use when configuring Firebase services (Firestore Client SDK with aggregations/vector search, Authentication, Storage, Cloud Functions v2, FCM push notifications, App Check bot protection), implementing security rules and indexes, troubleshooting Firebase errors, setting up auth providers (email/password, Google Sign-In), configuring VAPID keys for notifications, custom action URLs, reCAPTCHA Enterprise, replay protection, or resolving permission issues. Covers TypeScript patterns, Next.js 16 SSR/App Router integration, and common pain points like CORS, duplicate documents, notification setup, and bot abuse prevention.

AI video generation with Sora, Veo, and Kling. Use when creating Reels, video prompts, or handling video generation workflows.

Use this skill when you are writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

CLAUDE.md にプロジェクトの現在の状態を反映する。簡潔さを保ち、詳細ドキュメントへの参照で重複を避ける。

Safely extend or refine AFI signal schemas and closely-related validators in afi-core, while preserving determinism, respecting PoI/PoInsight design, and obeying the AFI Droid Charter and AFI Core AGENTS.md boundaries.