/think
Engage in deep, structured reasoning using sequential thinking
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/think
Context preview
What this command does when you run it.
Engage in deep, structured reasoning using sequential thinking
Command definition
think.mdallowed-tools: mcp__sequential-thinking__sequentialthinking, Write, Read, Bash(gdate:*)
name: "Think"
description: "Engage in deep, structured reasoning using sequential thinking"
author: "wcygan"
tags: ["analyze","think"]
version: "1.0.0"
created_at: "2025-07-14T00:00:00Z"
updated_at: "2025-07-14T00:00:00Z"
Context
- Session ID: !`gdate +%s%N`
- Working directory: !`pwd`
- Current time: !`gdate '+%Y-%m-%d %H:%M:%S'`
Your Task
STEP 1: Initialize Thinking Session
- Create thinking state file: /tmp/think-session-$SESSION_ID.json
- Initialize with topic: $ARGUMENTS
- Set thinking depth based on complexity assessment
STEP 2: Adaptive Deep Thinking Strategy
**FOR complex multi-dimensional problems requiring comprehensive analysis:**
**CRITICAL: Combine sequential thinking with parallel perspective analysis for maximum insight generation**
EXECUTE hybrid approach:
1. **Initial Sequential Thinking Phase**: Use sequential thinking tool for core problem exploration
- Start with 8-12 initial thoughts for comprehensive problem mapping
- Allow thinking to evolve organically - adjust total_thoughts as needed
- Question and revise previous thoughts when new insights emerge
- Generate multiple solution hypotheses and verify them systematically
2. **Parallel Perspective Analysis**: Deploy specialized thinking agents for different analytical dimensions
- **Agent 1: First Principles Analysis**: Break down problem to fundamental components and build up solutions
- **Agent 2: Systems Thinking**: Analyze interconnections, feedback loops, and emergent properties
- **Agent 3: Stakeholder Analysis**: Examine multiple stakeholder viewpoints, incentives, and constraints
- **Agent 4: Temporal Analysis**: Investigate past trends, current state, and future implications
- **Agent 5: Risk & Scenario Analysis**: Explore potential failure modes, edge cases, and alternative scenarios
3. **Integration & Synthesis**: Combine sequential insights with parallel perspectives for breakthrough understanding
**Sub-Thinking Coordination:**
- Sequential thinking provides deep logical progression and insight evolution
- Parallel agents provide comprehensive perspective coverage and analytical rigor
- Combined approach delivers both depth and breadth for complex problem solving
- Results synthesized into actionable insights with multiple validation approaches
**FOR straightforward problems requiring focused analysis:**
Use enhanced sequential thinking approach:
- Start with 5-8 initial thoughts for problem exploration
- Allow thinking to evolve organically - adjust total_thoughts as needed
- Question and revise previous thoughts when new insights emerge
- Generate solution hypotheses and verify them
- Continue until reaching satisfactory understanding
Key thinking approaches to incorporate:
- First principles analysis
- Systems thinking (interconnections and emergent properties)
- Contrarian perspectives and devil's advocate
- Temporal analysis (past trends, future implications)
- Stakeholder viewpoints and incentives
- Analogical reasoning from other domains
STEP 3: Synthesize Insights
FOR EACH major insight discovered:
- Document the breakthrough realization
- Explain why it's significant
- Identify implications and next steps
STEP 4: Create Actionable Output
Generate structured output including:
- Key insights and novel perspectives
- Critical factors and leverage points
- Practical recommendations
- Open questions requiring further exploration
Thinking Depth Guidelines
IF topic is straightforward:
- Use standard thinking mode (5-8 thoughts)
ELSE IF topic involves complex systems or decisions:
- Use extended thinking with revision cycles
- Allow 10-15+ thoughts with backtracking
ELSE IF topic requires breakthrough insights:
- Use maximum thinking depth
- Encourage branching and alternative paths
- Continue until novel connections emerge
Output Structure
# Deep Analysis: [Topic]
## Core Insights
1. **[Primary Breakthrough]**
- What: [Key realization]
- Why: [Significance and implications]
- How: [Practical applications]
2. **[Secondary Insight]**
- [Brief description and importance]
## Critical Factors
- [Highest leverage points for action]
- [Key variables that determine outcomes]
- [Important trade-offs and tensions]
## Recommendations
### Immediate Actions
1. [Next steps to take]
2. [Experiments to run]
3. [Information to gather]
### Strategic Implications
- [How this changes approach]
- [New opportunities to pursue]
- [Risks to monitor]
## Open Questions
- [Areas requiring further exploration]
- [Assumptions to validate]
- [Scenarios to consider]
Integration with Workflow
- Combine with `/investigate` for evidence-based input
- Follow with `/plan` to organize implementation
- Use `/deep-dive` for specific aspects needing more exploration
- Apply insights in `/options` for decision-making
The goal is breakthrough understanding through rigorous, multi-perspective analysis that leads to better decisions and creative solutions.
Read more
allowed-tools: mcp__sequential-thinking__sequentialthinking, Write, Read, Bash(gdate:*) name: "Think" description: "Engage in deep, structured reasoning using sequential thinking" author: "wcygan" tags: ["analyze","think"] version: "1.0.0" created_at: "2025-07-14T00:00:00Z" updated_at: "2025-07-14T00:00:00Z"
Context
- Session ID: !`gdate +%s%N`
- Working directory: !`pwd`
- Current time: !`gdate '+%Y-%m-%d %H:%M:%S'`
Your Task
STEP 1: Initialize Thinking Session
- Create thinking state file: /tmp/think-session-$SESSION_ID.json
- Initialize with topic: $ARGUMENTS
- Set thinking depth based on complexity assessment
STEP 2: Adaptive Deep Thinking Strategy
**FOR complex multi-dimensional problems requiring comprehensive analysis:**
**CRITICAL: Combine sequential thinking with parallel perspective analysis for maximum insight generation**
EXECUTE hybrid approach:
1. **Initial Sequential Thinking Phase**: Use sequential thinking tool for core problem exploration
- Start with 8-12 initial thoughts for comprehensive problem mapping
- Allow thinking to evolve organically - adjust total_thoughts as needed
- Question and revise previous thoughts when new insights emerge
- Generate multiple solution hypotheses and verify them systematically
2. **Parallel Perspective Analysis**: Deploy specialized thinking agents for different analytical dimensions
- **Agent 1: First Principles Analysis**: Break down problem to fundamental components and build up solutions
- **Agent 2: Systems Thinking**: Analyze interconnections, feedback loops, and emergent properties
- **Agent 3: Stakeholder Analysis**: Examine multiple stakeholder viewpoints, incentives, and constraints
- **Agent 4: Temporal Analysis**: Investigate past trends, current state, and future implications
- **Agent 5: Risk & Scenario Analysis**: Explore potential failure modes, edge cases, and alternative scenarios
3. **Integration & Synthesis**: Combine sequential insights with parallel perspectives for breakthrough understanding
**Sub-Thinking Coordination:**
- Sequential thinking provides deep logical progression and insight evolution
- Parallel agents provide comprehensive perspective coverage and analytical rigor
- Combined approach delivers both depth and breadth for complex problem solving
- Results synthesized into actionable insights with multiple validation approaches
**FOR straightforward problems requiring focused analysis:**
Use enhanced sequential thinking approach:
- Start with 5-8 initial thoughts for problem exploration
- Allow thinking to evolve organically - adjust total_thoughts as needed
- Question and revise previous thoughts when new insights emerge
- Generate solution hypotheses and verify them
- Continue until reaching satisfactory understanding
Key thinking approaches to incorporate:
- First principles analysis
- Systems thinking (interconnections and emergent properties)
- Contrarian perspectives and devil's advocate
- Temporal analysis (past trends, future implications)
- Stakeholder viewpoints and incentives
- Analogical reasoning from other domains
STEP 3: Synthesize Insights
FOR EACH major insight discovered:
- Document the breakthrough realization
- Explain why it's significant
- Identify implications and next steps
STEP 4: Create Actionable Output
Generate structured output including:
- Key insights and novel perspectives
- Critical factors and leverage points
- Practical recommendations
- Open questions requiring further exploration
Thinking Depth Guidelines
IF topic is straightforward:
- Use standard thinking mode (5-8 thoughts)
ELSE IF topic involves complex systems or decisions:
- Use extended thinking with revision cycles
- Allow 10-15+ thoughts with backtracking
ELSE IF topic requires breakthrough insights:
- Use maximum thinking depth
- Encourage branching and alternative paths
- Continue until novel connections emerge
Output Structure
# Deep Analysis: [Topic] ## Core Insights 1. **[Primary Breakthrough]** - What: [Key realization] - Why: [Significance and implications] - How: [Practical applications] 2. **[Secondary Insight]** - [Brief description and importance] ## Critical Factors - [Highest leverage points for action] - [Key variables that determine outcomes] - [Important trade-offs and tensions] ## Recommendations ### Immediate Actions 1. [Next steps to take] 2. [Experiments to run] 3. [Information to gather] ### Strategic Implications - [How this changes approach] - [New opportunities to pursue] - [Risks to monitor] ## Open Questions - [Areas requiring further exploration] - [Assumptions to validate] - [Scenarios to consider]
Integration with Workflow
- Combine with `/investigate` for evidence-based input
- Follow with `/plan` to organize implementation
- Use `/deep-dive` for specific aspects needing more exploration
- Apply insights in `/options` for decision-making
The goal is breakthrough understanding through rigorous, multi-perspective analysis that leads to better decisions and creative solutions.
A lightweight (~46kB) and comprehensive CLI tool for managing Claude commands, configurations, and workflows.
Repo: kiliczsh/claude-cmd
Other commands on claude-cmd.
- /agent-browser-automation
Automate browser interactions for development testing using Puppeteer MCP
Open command - /agent-prep-merge
Prepare branches for merging across multiple worktrees and coordinate integration
Open command - /agent-persona-accessibility-expert
Transform into accessibility expert for WCAG compliance and inclusive design
Open command - /agent-persona-api-designer
Transform into an API design specialist who creates well-structured, developer-friendly APIs
Open command - /agent-persona-backend-specialist
Transform into backend specialist for scalable API and system design
Open command - /agent-persona-cloud-architect
Cloud architect persona for designing scalable, secure cloud infrastructure using modern cloud-native technologies
Open command

