文件

Convert Product Requirements Documents (PRDs) into technical blueprints and implementation plans

Autonomously execute exploratory implementation of one approach from spike definition, working independently until natural stop. Use when partner provides spike definition and assigns you an approach number to explore in isolation, when comparing multiple implementation alternatives, or when evaluating technical feasibility before committing to an approach

Reference and maintain consistency with the project's technical stack including frameworks, runtimes, languages, frontend libraries, databases, ORMs, testing tools, deployment platforms, and third-party services. Use this skill when making technology choices or selecting libraries that need to align with the existing stack, adding new dependencies to package.json, pnpm-workspace.yaml, requirements.txt, or other dependency management files, implementing features using the project's established frameworks, ORMs, databases, or APIs, writing code in the project's primary language and runtime environment, setting up testing infrastructure with the project's test frameworks, configuring CI/CD pipelines or deployment settings, integrating third-party services that match the project's existing integrations, ensuring compatibility with the project's build tools and bundlers, or ensuring any technical implementation decision aligns with the project's established technologies, architectural patterns, and conventions doc

Generate comprehensive, publication-quality technical manuals with thematic storytelling using multi-agent orchestration. Use when user asks for themed documentation, narrative technical guides, memorable training materials, or mentions themes like Victorian, steampunk, art deco, medieval, pharmaceutical, or nautical combined with technical topics. Triggers on phrases like "create themed manual", "documentation with storytelling", or requests to make docs "more engaging" or "memorable".

Analyze text to identify technical domains and suggest appropriate specialized agentsfor delegation following Constitutional Principle X (Agent Delegation Protocol).This skill examines specifications, plans, tasks, or any technical text to detectdomain keywords and recommend whether to use single-agent or multi-agent delegation.It ensures specialized work is routed to specialists rather than handled by generalists.Triggered by: User request for "which agent?", "who should do this?", domainidentification needs, or automatically by /specify, /plan, /tasks commands.

Generate intelligent Python project documentation with UML class diagrams, architecture diagrams, and code analysis. Analyzes codebase structure to recommend and create appropriate visualizations for project overview.

Standards enforced when writing code, creating pull requests, committing changes, or documenting features. CRITICAL - No emoji in developer-facing content (code/docs/PRs/issues/commits) or CLI output. Also defines standards for using cutting-edge language features and writing comprehensive documentation. Should be applied to all development work.

EU MDR 2017/745 regulation specialist and consultant for medical device requirement management. Provides comprehensive MDR compliance expertise, gap analysis, technical documentation guidance, clinical evidence requirements, and post-market surveillance implementation. Use for MDR compliance assessment, classification decisions, technical file preparation, and regulatory requirement interpretation.

Comprehensive NestJS framework skill for building scalable server-side applications. Use for TypeScript backend development with controllers, providers, modules, dependency injection, middleware, guards, interceptors, pipes, database integration (MikroORM + MongoDB), GraphQL, microservices, testing, and API documentation. Also triggers when working with NestJS TypeScript files (.ts), NestJS module files, nest-cli.json, or NestJS project structure. Example triggers: "Create NestJS controller", "Set up dependency injection", "Add middleware", "Create GraphQL resolver", "Build microservice", "Write NestJS test", "Set up database module"

Write self-documenting code with minimal, helpful comments that explain large sections of logic without cluttering the codebase. Use this skill when writing code comments, documenting complex logic, reviewing whether comments are needed, writing function documentation, explaining non-obvious code sections, ensuring code clarity through naming and structure, avoiding temporary or change-related comments, keeping comments evergreen and future-relevant, or deciding between adding comments versus refactoring for clarity. Apply this skill when writing or reviewing any code file to ensure comments add value without creating noise, and that code is primarily self-explanatory through clear naming and structure.

Compose weeknotes blog posts in Jekyll-style Markdown from multiple data sources including Mastodon and Linkding. Use this skill when the user requests to create, draft, or generate weeknotes content for a blog post.

Embed the chatbot UI inside Docusaurus and connect it to the FastAPI RAG backend. Use when building chat components, handling streaming responses, or integrating chat widgets into MDX pages.

Controlled batch execution of implementation plans with review checkpoints between phases. Loads plan, critically reviews for issues, executes tasks in batches, then pauses for architect feedback before continuing. Use when you have a complete implementation plan from brainstorming/writing-plans and want structured execution with quality gates. Do NOT use for ad-hoc implementation, exploratory coding, or when you don't have a formal plan - just implement directly with code review at the end.

Patterns for implementing Toolsmith library functions. Covers pragmatic internal approach using raw operators with exception documentation, monadic behavior patterns (Result/Validation/plain value), predicate special rules, and the distinction between building Toolsmith vs consuming it. Use when implementing functions FOR the Toolsmith library itself.

Use when rewriting commit history — rewording, splitting, squashing, or cleaning messages — in a safe, bounded, and observable way without touching remotes.

Generates comprehensive Map of Content (MOC) documentation for software projects using standard markdown links, analyzing current implementation state from codebase and devlog notes

Unit testing patterns with Vitest. Use when writing tests for TypeScript code.

This skill should be used when developing or modifying dotfiles using chezmoi. Covers using .chezmoidata for configuration data and modify_ scripts (or run_onchange_after_ scripts for symlinked directories) for non-destructive file merging. Particularly useful when needing to configure application settings without overwriting user preferences.

Central coordinator for blog writing workflow with multi-agent execution. USE WHEN user says 'write a blog post', 'create blog content', 'start blog workflow', OR user wants to orchestrate the full blog writing pipeline.

Conventional Commits 1.0.0 に準拠した日本語コミットメッセージを作成します。タイプ（feat/fix/docs/style/refactor/perf/test/build/ci/chore）の選択、スコープの設定、破壊的変更の記載を行います。git commit を行う際、コミットメッセージの作成を依頼されたとき、変更内容を要約してコミットしたいときに使用してください。