Research

構造化ライティングを実践するためのスキル。DITAやトピックベースの原則に沿って文書を分割・再利用し、手順/概念/参照の役割を明確にする。Anchors:• DITA 1.3 Specification / 適用: トピック設計 / 目的: 文書構造の標準化• Information Architecture for the World Wide Web / 適用: 情報設計 / 目的: 探しやすさの向上• Topic-Based Authoring / 適用: 再利用設計 / 目的: モジュール化と保守性の改善Trigger:Use when designing topic-based documentation, modular content, or reusable docs with clear task/concept/reference separation.structured writing, DITA, topic-based authoring, content reuse, documentation structure

PhD-level academic manuscript and research proposal review.

Research ethics, IRB compliance, and data privacy analysis.

This skill automates the setup of machine learning experiment tracking using tools like MLflow or Weights & Biases (W&B). It is triggered when the user requests to "track experiments", "setup experiment tracking", "initialize MLflow", or "integrate W&B". The skill configures the necessary environment, initializes the tracking server (if needed), and provides code snippets for logging experiment parameters, metrics, and artifacts. It helps ensure reproducibility and simplifies the comparison of different model runs.

Conduct user research and validation. Use when discovering user needs, validating assumptions, creating personas, or understanding pain points. Covers interviews, surveys, analysis, and synthesis.

Use after brainstorming is complete but before planning implementation, when you need technical details about integration points, APIs, data shapes, or existing patterns - produces directive specification with all ambiguities extracted to structured clarification file

Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments.

MeshCore protocol reference for repeater/room server dashboard development. Use when working with packet structure, payload types, routing, path analysis, neighbor detection, topology computation, or pyMC_Repeater API integration.

Master memory management, pointers, references, smart pointers, and safe dynamic memory allocation in C++.

Guided onboarding for new users. Collects reference documents, builds CANDIDATE-PROFILE.md from them, configures agents. Use for: "set up", "initialize", "get started", "configure my profile".

Extract and maintain company-specific coding best practices from PR review comments. Use when the user requests to analyze PR comments from a repository to generate best practices documentation, or when implementing features and needs to reference established coding standards. Triggers include requests like "analyze PR comments and create best practices", "extract coding standards from repo X", or "check if this code follows our best practices".

Apply consistent documentation standards and style guidelines when creating, reviewing, or improving project documentation (README, architecture docs, guides, references). This skill should be used when writing new documentation, reviewing existing docs for style consistency, or when users request documentation improvements or style guide compliance checks.

Validates research/plan/code against overengineering, underengineering, and hallucination

Initialize session as ORCHESTRATOR agent with multi-agent coordination capability. Use for complex tasks requiring parallel agent spawning and result synthesis.

Automatically validates Cloudflare Workers binding configuration, ensuring code references match wrangler.toml setup and TypeScript interfaces are accurate

Authoritative reference for Anthropic products. Use when users ask about product capabilities, access, installation, pricing, limits, or features. Provides source-backed answers to prevent hallucinations about Claude.ai, Claude Code, and Claude API.

Specializes in agent dependency and interface design. Defines skill references, command coordination, and inter-agent collaboration protocols while preventing circular dependencies to build effective multi-agent systems.Anchors:• "The Pragmatic Programmer" (Andrew Hunt, David Thomas) / Application: Procedure design and practical improvement / Purpose: Build effective agent collaboration mechanisms• "Software Architecture in Practice" (Len Bass, Paul Clements, Rick Kazman) / Application: Interface design patterns / Purpose: Minimize dependencies and improve maintainabilityTrigger:Use when defining inter-agent data handoffs, designing multi-agent collaboration, detecting or resolving circular dependencies, or defining handoff protocols.agent collaboration, dependency graph, handoff protocol, circular dependency, skill reference, multi-agent system

スキルを作成・更新・プロンプト改善するためのメタスキル。 3つのモード（create/update/improve-prompt）を提供し、 Script Firstで100%再現可能な実行を実現する。 Anchors: • Continuous Delivery (Jez Humble) / 適用: 自動化パイプライン / 目的: 決定論的実行 • The Lean Startup (Eric Ries) / 適用: Build-Measure-Learn / 目的: 反復改善 • Domain-Driven Design (Eric Evans) / 適用: ユビキタス言語 / 目的: 一貫した語彙 Trigger: 新規スキルの作成、既存スキルの更新、プロンプト改善を行う場合に使用。 スキル作成, スキル更新, プロンプト改善, skill creation, skill update, improve prompt

Initialize session as ORCHESTRATOR agent with multi-agent coordination capability. Use for complex tasks requiring parallel agent spawning and result synthesis.

Use when the user needs technical research, architecture validation, documentation generation, or code review. Default is read-only mode, but can enable auto-approve (-y) for code changes.