Claude Agent SDK（@anthropic-ai/claude-agent-sdk）および直接Anthropic SDK（@anthropic-ai/sdk）を使用したエージェント統合の実装を専門とするスキル。 query() API、Hooksシステム、Permission Control、Electron統合、ストリーミング処理、Direct SDKパターンを支援します。 Anchors: • Claude Agent SDK Official Docs / 適用: SDK API、Hooks、Permissions / 目的: 公式パターンに準拠した実装 • Anthropic SDK (@anthropic-ai/sdk) / 適用: Direct SDK呼び出し / 目的: シンプルなMain Process統合 • Electron IPC Best Practices / 適用: Main-Renderer間通信 / 目的: セキュアなプロセス間通信 • TypeScript Handbook / 適用: 型定義、ジェネリクス / 目的: 型安全なSDK統合 Trigger: Claude Agent SDKを使用したエージェント機能実装、query() APIストリーミング処理、Hooksシステム実装、Electron統合、Permission Control設計、MCP統合、Direct SDK統合を行う場合に使用。 claude-agent-sdk, query API, PreToolUse, PostToolUse, PermissionRequest, Electron IPC, MCP, ストリーミング, 権限制御, @anthropic-ai/sdk, Direct SDK

更新 ROADMAP.md 狀態。觸發：roadmap、路線、規劃、里程碑。

Synthesizes all pipeline handoffs into a single human-readable project brief. Use when user says "generate docs", "create documentation", "document the project", or after validation passes. Do NOT use for deployment (use fabric-deploy) or architecture design (use fabric-design).

Apply task-specific templates to AI session plans using ai-update-plan. Use when starting a new task to load appropriate plan structure (feature, bugfix, refactor, documentation, security).

Python coding standards for Amplifier including type hints, async patterns, error handling, and formatting. Use when writing Python code for Amplifier modules.

Comprehensive project design and ideation skill for AI/ML and web/mobile applications. Use when users present initial project ideas that need enhancement, architectural guidance, technology stack recommendations, feature expansion, or implementation strategy. Triggers include requests like "help me design a [project type]", "I want to build [concept] but need to flesh out the idea", "what features should I add to [project]", "recommend a tech stack for [idea]", or "enhance my project concept". Provides structured design thinking, architectural patterns, feature frameworks, and technology recommendations through progressive disclosure of specialized reference materials.

Run a live Looper-Go smoke test by creating a temporary project (PROJECT.md + to-do.json), executing looper for one iteration, observing output, and reporting results. Use when verifying looper-go behavior or demonstrating a live run.

Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection.

Create video clips from chapter timestamps using ffmpeg. Use when given a video file and timestamps/chapters to split into separate clips.

Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.

Use for LARGE work requiring feature-level grouping. Creates epic tracking issues, manages related issues under a common label, tracks epic progress, and coordinates with milestones.

Add a new blog post to this Docusaurus site from a staging folder.

Use when setting up DocC documentation for a Swift package, deploying to GitHub Pages, or encountering "no such module 'UIKit'" during doc generation

Use when writing or enhancing Swift documentation comments for DocC generation, adding inline doc comments to Swift source files, or when user asks for API documentation

Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b], [project-c], Claude Code), requests investigations, or queries past lessons. Returns structured, actionable insights achieving 69-94% context reduction. (project, gitignored)

The Engineer skill — deploys Fabric items in dependency-ordered waves and remediates issues found during validation. Use when user says "deploy", "create items", "run deployment", "fix deployment issues", "remediate", or after user sign-off is complete. Do NOT use for design (use fabric-design) or testing (use fabric-test).

Guide for creating new Amplifier modules including protocol implementation, entry points, mount functions, and testing patterns. Use when creating new modules or understanding module architecture.

List and review Advanced Security alerts for an Azure DevOps repository. Shows dependency vulnerabilities, secret exposure, and code scanning findings with filtering by severity, state, and alert type.

The QA skill — reviews architecture for testability, creates test plans from acceptance criteria, and validates deployments. Use when user says "create test plan", "validate deployment", "run validation", "review architecture", "check items", "what should we test", or after architecture is finalized or deployment is complete. Do NOT use for architecture design (use fabric-design) or deployment (use fabric-deploy).

Summarize a single Azure DevOps work item (and its links and comments) by ID.