Loading...
Loading...
Found 339 Skills
GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully.
Apply UX psychology effects to UI design. Automatically reference when designing landing pages, pricing tables, onboarding flows, and CTAs.
Model Context Protocol (MCP) サーバーの作成・管理ガイド。カスタムツールの追加方法。 使用タイミング: (1) Claude Codeにカスタムツールを追加したい時 (2) 外部サービス連携時 (3) プロジェクト固有の自動化ツールを作りたい時 (4) MCPサーバーの設定方法を知りたい時。 トリガー例: 「MCPサーバーを作って」「カスタムツールを追加」「MCP設定」 「外部APIをツール化」「テストランナーMCP」
Git worktree を使った複数ブランチの同時作業管理。 使用タイミング: (1) 複数機能を並行開発したい時 (2) PRレビュー中に別作業したい時 (3) 本番ホットフィックスと開発を同時進行したい時 (4) worktreeの使い方を知りたい時。 トリガー例: 「worktreeで」「別ブランチを同時に」「並行開発したい」 「PRレビューしながら開発」「ホットフィックス用のworktree」
A skill for creating note articles in the interview format of kimny × Claude (AI). It defines release judgment rules based on quality gates (discovery, external anchor, one-sentence test), AIO optimization specifications, and dialogue format rules. Usage scenarios: (1) Creation and rewrite of note articles (2) Structuring interview-style articles (3) Converting historical conversations into articles (4) Article quality check. Example triggers: "I want to turn this into an article", "I want to write on note", "Use interview format", "Can this be made into an article?", "Rewrite the article", "Pass the quality gate", "AIO optimization", "note article"
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
Manages IT infrastructure, monitoring, incident response, and service reliability. Provides frameworks for ITIL service management, observability strategies, automation, backup/recovery, capacity planning, and operational excellence practices.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.
This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and other single-cell modalities. Use this skill for probabilistic modeling, batch correction, dimensionality reduction, differential expression, cell type annotation, multimodal integration, and spatial analysis tasks.