sequential-thinking

Description

순차적 사고, 분석, 문제 해결, 복잡한 문제, 단계별 분석 - Use when solving complex problems. Systematic thinking workflow using Sequential Thinking MCP for multi-step analysis, trade-off evaluation, and architectural decisions.

AI Summary

Uses systematic multi-step analysis for complex problems like architecture decisions, bug root cause analysis, and trade-off evaluation. Triggers when solving problems requiring structured thinking, planning refactoring strategies, or interpreting uncertain requirements.

Install

Add the repository(one-time)

/plugin marketplace add aimskr/aims-toolkit

Install the plugin

/plugin install aims-toolkit@aims-toolkit

Tool Access

This skill inherits all available tools. When active, it can use any tool Claude has access to.

Skill Content

Sequential Thinking Workflow

Use Scenarios

Complex Design Decisions: Architecture selection, tech stack decisions
Multi-step Problem Solving: Bug root cause analysis, performance optimization strategy
Uncertain Requirements: Requirements interpretation, approach exploration
Trade-off Analysis: Comparing pros and cons of multiple options
Refactoring Planning: Code improvement strategy

Thinking Process

1. Problem Decomposition (estimate total_thoughts)
   ↓
2. Step-by-step Thinking (analyze with each thought)
   ↓
3. Verification/Revision (is_revision: true)
   ↓
4. Hypothesis Formation and Verification
   ↓
5. Final Answer (next_thought_needed: false)

Checklist

Before Starting:

Is the problem truly complex? (Answer simple questions directly)
Would step-by-step thinking help?
Estimate initial total_thoughts (5-15)

During Process:

Does each thought have a clear purpose?
Is it logically connected to previous thoughts?
When stuck: use revises_thought to reconsider
When exploring alternatives: use branch_from_thought
If more needed: needs_more_thoughts: true

At Completion:

Has a satisfactory answer been reached?
Has the hypothesis been sufficiently verified?
Set next_thought_needed: false

Effective Usage Tips

Add thoughts as needed, don't be constrained by initial estimates
Express uncertainty honestly when things aren't clear
Reconsider previous decisions using revises_thought
Use branching for alternative exploration (branch_from_thought, branch_id)
Ignore information irrelevant to the current step

What to Avoid

Using excessive thinking for simple questions
Prematurely ending the thinking process
Lack of logical connection to previous thoughts
Pretending certainty when uncertain

Integration with Serena MCP

For complex code work:

Sequential Thinking: Analyze requirements and establish approach strategy
Serena MCP: Explore code structure and current state
Sequential Thinking: Analyze exploration results and design modifications
Serena MCP: Perform actual code modifications

Links

GitHub Stats

0 forks

Updated 2 days ago

Similar Skills

Command Development

10 files

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

plugin-dev

54.1k

Agent Development

6 files

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

plugin-dev

54.1k

Hook Development

10 files

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

plugin-dev

54.1k