/ultrathink
Structured thinking process for complex challenges. Trigger with "think deeply", "analyze thoroughly", "complex problem", "consider from multiple angles".
$ npx -y skills add wasabeef/claude-code-cookbook --skill ultrathink --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/ultrathink
Context preview
The summary Claude sees to decide when to auto-load this skill.
Structured thinking process for complex challenges. Trigger with "think deeply", "analyze thoroughly", "complex problem", "consider from multiple angles".
SKILL.md
ultrathink.SKILL.mddescription: 'Structured thinking process for complex challenges. Trigger with "think deeply", "analyze thoroughly", "complex problem", "consider from multiple angles".'
Structured thinking process for complex challenges
Execute a step-by-step, structured thinking process for complex tasks and important decisions.
Usage
# Request deep thinking from Claude
"Analyze [task] using ultrathink"
Basic Examples
# Examine architecture design
"Analyze whether to choose microservices or monolith using ultrathink"
# Analyze technology selection
"Analyze whether Rust or TypeScript is suitable for this project using ultrathink"
# Deep dive into problem solving
"Analyze the causes of poor application performance and improvement methods using ultrathink"
Collaboration with Claude
# Business decisions
"Prioritize new features using ultrathink. Consider user value, development cost, and technical risk"
# System design
"Design an authentication system using ultrathink. Consider security, scalability, and maintainability"
# Trade-off analysis
"Analyze the choice between GraphQL vs REST API using ultrathink. Based on project requirements"
# Refactoring strategy
cat src/legacy_code.js
"Develop a refactoring strategy for this legacy code using ultrathink"
Thinking Process
1. **Problem Decomposition** - Break down tasks into components 2. **MECE Analysis** - Organize without gaps or overlaps 3. **Multiple Perspective Review** - Analyze from technical, business, and user perspectives 4. **Interactive Confirmation** - Confirm with users at important decision points 5. **Evidence-Based Proposal** - Conclusions based on data and logic
Detailed Examples
# Resolve complex technical debt
"Develop a strategy to modernize a 10-year legacy system using ultrathink. Include phased migration, risks, and ROI"
# Organizational challenges
"Develop a scaling strategy for the development team using ultrathink. Assume expansion from 5 to 20 people"
# Database migration
"Analyze migrating from PostgreSQL to DynamoDB using ultrathink. Consider cost, performance, and operational aspects"
Notes
Ultrathink is ideal for tasks that require deep thinking over time. For simple questions or immediate answers, use the normal question format.
Read more
description: 'Structured thinking process for complex challenges. Trigger with "think deeply", "analyze thoroughly", "complex problem", "consider from multiple angles".'
Structured thinking process for complex challenges
Execute a step-by-step, structured thinking process for complex tasks and important decisions.
Usage
# Request deep thinking from Claude "Analyze [task] using ultrathink"
Basic Examples
# Examine architecture design "Analyze whether to choose microservices or monolith using ultrathink" # Analyze technology selection "Analyze whether Rust or TypeScript is suitable for this project using ultrathink" # Deep dive into problem solving "Analyze the causes of poor application performance and improvement methods using ultrathink"
Collaboration with Claude
# Business decisions "Prioritize new features using ultrathink. Consider user value, development cost, and technical risk" # System design "Design an authentication system using ultrathink. Consider security, scalability, and maintainability" # Trade-off analysis "Analyze the choice between GraphQL vs REST API using ultrathink. Based on project requirements" # Refactoring strategy cat src/legacy_code.js "Develop a refactoring strategy for this legacy code using ultrathink"
Thinking Process
1. **Problem Decomposition** - Break down tasks into components 2. **MECE Analysis** - Organize without gaps or overlaps 3. **Multiple Perspective Review** - Analyze from technical, business, and user perspectives 4. **Interactive Confirmation** - Confirm with users at important decision points 5. **Evidence-Based Proposal** - Conclusions based on data and logic
Detailed Examples
# Resolve complex technical debt "Develop a strategy to modernize a 10-year legacy system using ultrathink. Include phased migration, risks, and ROI" # Organizational challenges "Develop a scaling strategy for the development team using ultrathink. Assume expansion from 5 to 20 people" # Database migration "Analyze migrating from PostgreSQL to DynamoDB using ultrathink. Consider cost, performance, and operational aspects"
Notes
Ultrathink is ideal for tasks that require deep thinking over time. For simple questions or immediate answers, use the normal question format.
A collection of commands, roles, and automation scripts for Claude Code. Automate your workflow without unnecessary confirmations, allowing you to focus on what matters.
Repo: wasabeef/claude-code-cookbook
Other skills on claude-code-cookbook.
- /analyze-dependencies
Analyze project dependencies and evaluate architectural health. Trigger with "analyze dependencies", "detect circular dependencies", "architecture issues?", "check module coupling", "find layer violations". Generates dependency matrix, fan-in/fan-out analysis, and prioritized
Open skill - /analyze-performance
Performance analysis based on Core Web Vitals with UX scoring. Trigger with "analyze performance", "improve speed", "check Core Web Vitals", "page speed", "improve LCP", "identify performance issues".
Open skill - /check-fact
Verify information accuracy against codebase and documentation. Trigger with "is this correct?", "fact check", "verify this", "is this accurate?".
Open skill - /check-prompt
Evaluate and improve AI prompt quality. Trigger with "check this prompt", "evaluate prompt quality", "improve this prompt".
Open skill - /commit-message
Generate commit messages from staged changes. Trigger with "suggest commit message", "generate commit message", "what should the commit say?", "write commit message".
Open skill - /context7
Search technical documentation via Context7 MCP. Trigger with "check the docs", "look up documentation", "how to use this library?", "API reference".
Open skill

