Development

This skill should be used for prior investigation, scope quantification, and detailed planning before implementation. Use when you need to analyze a problem, estimate complexity, and create a comprehensive implementation plan. Designed for expensive/clever models (Opus, Sonnet) to maximize planning quality.

Runtime security validation including secret scanning, PII detection, prompt injection defense, audit logging, and output validation for AI agents. Use when validating user input, scanning for secrets, detecting PII, preventing data exfiltration, or implementing security guardrails.

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.

Natural language search through Claude Code session history. Search for previous prompts, conversations, topics, file modifications, and context from past sessions. Useful for finding earlier work and understanding project continuity.

Teach parallel routes and slot patterns in Next.js 16. Use when implementing parallel routes, working with @slot syntax, or encountering missing default.tsx errors.

Perform a repo-wide, evidence-based audit of documentation against the current codebase and recent changes. Produces a proposed, fully rewritten documentation set in TempDoc-ForUserReview and asks for approval before any changes are applied to the existing docs.

Create and modify 3D parametric models in the threedee design environment. Use when: (1) creating new 3D objects, geometries, or meshes, (2) modifying parameters like dimensions, colors, materials, (3) adding primitives (boxes, spheres, cylinders, torus knots), (4) setting up lighting or camera, (5) exporting models to STL/OBJ/glTF, (6) working with Three.js code in this project. Triggers on requests involving 3D modeling, CAD-like operations, parametric design, or mesh creation.

Generate PostCSS configuration files with plugins for CSS processing, autoprefixing, and optimizations. Triggers on "create postcss config", "generate postcss configuration", "postcss setup", "css processing config".

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.

PRをレビューする。変更されたコードに対してmacOS/Swift/SwiftUI固有の問題を検出し、日本語でフィードバックを提供する。

Deploy the shot-elixir Elixir/Phoenix application to Fly.io. Use this skill when deploying backend changes, updating environment variables, or releasing new versions to production.

Reviews code for quality issues, potential bugs, security vulnerabilities, and adherence to best practices. Provides actionable feedback with specific line references.

Pre-implementation research for design, architecture, and impact analysis. Use during brainstorming, architectural design, or before implementation to understand dependencies and integration points. Triggers on (1) designing or architecting a feature, (2) brainstorming implementation approaches, (3) analyzing impact of proposed changes, (4) exploring reference materials in extra/, (5) creating research reports before planning.

Reproduce research papers into working code. Use when user wants to implement ML/AI papers, reproduce experiments, extract algorithms from PDFs, or convert research into executable code. Handles multiple interconnected papers with multi-agent extraction, equation verification, and benchmark validation.

This skill should be used when developing Electron applications with Feature-Sliced Design (FSD) architecture and React 19. Triggers on requests to create components, features, entities, widgets, or pages following FSD layer structure. Also applies when setting up Electron main/preload/renderer process code organization.

Generate professional HTML presentation slides from Markdown files or raw content. Use when creating presentations, slide decks, or when asked to make slides. Fully automated workflow - Markdown analysis → Layout selection → HTML generation → Thumbnail generation → Surge deployment. Supports 16 layouts, Chart.js graphs, and interactive features.

Systematic code quality improvement workflow combining smart-reviewer and test-generator MCP tools with Pareto 80/20 auto-fixes, severity-based review, and comprehensive test generation. Use when p...

Diagnose and fix broken bone/blend shape/annotation mappings on 3D characters. Analyzes model data, compares against presets, extracts animation data, and generates corrected mappings. Use when annotations don't work, AUs don't animate correctly, or importing new character models. Primary focus on skeletal-only models like the Betta fish.

Expert in Lighthouse Journey Timeline frontend architecture, React patterns, TypeScript, TanStack Query, Zustand, and component development with strong type safety. Use when building UI components, implementing data fetching, managing state, writing forms, styling with Tailwind, testing React components, or integrating with backend APIs.

Download audio and video from thousands of websites using yt-dlp. Feature-rich command-line tool supporting format selection, subtitle extraction, playlist handling, metadata embedding, and post-processing. This skill is triggered when the user says things like "download this video", "download from YouTube", "extract audio from video", "download this playlist", "get the mp3 from this video", "download subtitles", or "save this video locally".