Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity...
Multi-agent research that keeps bringing gifts back — like cats! Dispatch multiple agents to research a topic in parallel, compile findings, and iterate on new discoveries.
Claude in Chrome - browser automation via the official Anthropic extension. Control your logged-in Chrome browser, automate workflows, fill forms, extract data, and run scheduled tasks.
Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images,...
World-class video directing mastery drawing from cinematic legends like Spielberg, Cameron, Coppola, and Nolan. This skill translates directorial intent into AI video generation, focusing on...
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types...
Génère des images heroic fantasy pour BFRPG via fal.ai FLUX.1. Portraits de personnages/PNJ, scènes d'aventure, monstres, objets magiques et lieux. Utilise des prompts optimisés pour le style...
Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with...
Use Laravel-specific vocabulary—Eloquent patterns, Form Requests, API resources, jobs/queues—to get idiomatic framework code
Detect and surface potential decision-making in work items, plans, diffs, docs, or summaries. Use to flag possible decisions neutrally without enforcing process.
codex reviewを活用したコードレビューエージェント。PRレビュー自動化・コミット前チェックを担当。バグ検出、セキュリティ脆弱性、ロジックエラー、意図との不整合を発見。Zenのリファクタリング提案を補完。コードレビュー、品質チェックが必要な時に使用。
既存データ/ロジックを活用した新機能をMarkdown仕様書で提案。新機能のアイデア出し、プロダクト企画、機能提案が必要な時に使用。コードは書かない。
API設計・レビュー、OpenAPI仕様生成、バージョニング戦略、破壊的変更検出、REST/GraphQLベストプラクティス適用。API開発の品質と一貫性を確保。API設計、OpenAPI仕様が必要な時に使用。
クラウドインフラ（Terraform/CloudFormation/Pulumi）とローカル開発環境（Docker Compose/dev setup/環境変数）両面の環境プロビジョニングを担当。IaC設計、環境構築、マルチクラウド対応が必要な時に使用。
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image...
Microsoft Teams bots and AI agents - Claude/OpenAI, Adaptive Cards, Graph API