sequential-thinking
mrgoonie/claudekit-skills
Structured step-by-step reasoning with revision and branching for complex multi-stage problems.
What is sequential-thinking?
Enables iterative problem-solving through sequential thought steps with the ability to revise conclusions, explore alternative approaches, and dynamically adjust scope. Use when tackling complex problems that require systematic decomposition, multi-stage analysis, or design planning where the full scope may not be clear upfront.
- Break complex problems into sequential reasoning steps with numbered tracking
- Dynamically adjust estimated total thought count as understanding evolves
- Revise and reconsider previous conclusions by referencing specific thought numbers
- Branch into alternative reasoning paths from any point in the analysis
- Maintain full context of the reasoning chain throughout the problem-solving process
How to install sequential-thinking
npx skills add https://github.com/mrgoonie/claudekit-skills --skill sequential-thinkingHow to use sequential-thinking
- 1.Call mcp__reasoning__sequentialthinking with your initial thought, setting thoughtNumber to 1
- 2.Estimate totalThoughts based on problem complexity; this can be adjusted later
- 3.Express your current reasoning clearly in the thought parameter
- 4.Set nextThoughtNeeded to true to continue iterating or false when you reach a conclusion
- 5.For revisions, set isRevision to true and specify which thought number you're reconsidering
- 6.For branching, set branchFromThought to the step you're diverging from and provide a branchId
- 7.Continue calling the tool with incremented thoughtNumber until nextThoughtNeeded is false
Use cases
- Multi-stage system design where architecture decisions depend on earlier analysis
- Debugging complex issues by systematically narrowing down root causes
- Algorithm optimization where initial approach proves suboptimal and requires backtracking
- Research or analysis tasks with initially unclear scope that expand during investigation
- Problem decomposition where alternative solution paths need exploration before committing
- Software architects and system designers
- Researchers and analysts tackling complex problems
- Engineers debugging multi-layered issues
- Anyone solving problems with uncertain scope or multiple viable approaches
sequential-thinking FAQ
Yes. Adjust totalThoughts dynamically as your understanding evolves. Accuracy of the estimate matters less than making progress visible.
Use revision when an earlier assumption proves incorrect and you need to reconsider that specific step. Use branching when multiple viable approaches exist and you want to explore alternatives without abandoning the original path.
This skill provides structured tracking of your reasoning chain with explicit revision and branching capabilities, making it easier to backtrack, explore alternatives, and maintain context across complex multi-step problems.
No. This skill is designed for complex problems requiring multiple interconnected reasoning steps. For simple queries or direct facts, standard reasoning is more efficient.
Set nextThoughtNeeded to false when you've reached a conclusion or solution. You don't need to hit your estimated totalThoughts exactly—stop when the problem is adequately resolved.
Full instructions (SKILL.md)
Source of truth, from mrgoonie/claudekit-skills.
name: sequential-thinking description: Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope. license: MIT
Sequential Thinking
Enables structured problem-solving through iterative reasoning with revision and branching capabilities.
Core Capabilities
- Iterative reasoning: Break complex problems into sequential thought steps
- Dynamic scope: Adjust total thought count as understanding evolves
- Revision tracking: Reconsider and modify previous conclusions
- Branch exploration: Explore alternative reasoning paths from any point
- Maintained context: Keep track of reasoning chain throughout analysis
When to Use
Use mcp__reasoning__sequentialthinking when:
- Problem requires multiple interconnected reasoning steps
- Initial scope or approach is uncertain
- Need to filter through complexity to find core issues
- May need to backtrack or revise earlier conclusions
- Want to explore alternative solution paths
Don't use for: Simple queries, direct facts, or single-step tasks.
Basic Usage
The MCP tool mcp__reasoning__sequentialthinking accepts these parameters:
Required Parameters
thought(string): Current reasoning stepnextThoughtNeeded(boolean): Whether more reasoning is neededthoughtNumber(integer): Current step number (starts at 1)totalThoughts(integer): Estimated total steps needed
Optional Parameters
isRevision(boolean): Indicates this revises previous thinkingrevisesThought(integer): Which thought number is being reconsideredbranchFromThought(integer): Thought number to branch frombranchId(string): Identifier for this reasoning branch
Workflow Pattern
1. Start with initial thought (thoughtNumber: 1)
2. For each step:
- Express current reasoning in `thought`
- Estimate remaining work via `totalThoughts` (adjust dynamically)
- Set `nextThoughtNeeded: true` to continue
3. When reaching conclusion, set `nextThoughtNeeded: false`
Simple Example
// First thought
{
thought: "Problem involves optimizing database queries. Need to identify bottlenecks first.",
thoughtNumber: 1,
totalThoughts: 5,
nextThoughtNeeded: true
}
// Second thought
{
thought: "Analyzing query patterns reveals N+1 problem in user fetches.",
thoughtNumber: 2,
totalThoughts: 6, // Adjusted scope
nextThoughtNeeded: true
}
// ... continue until done
Advanced Features
For revision patterns, branching strategies, and complex workflows, see:
- Advanced Usage - Revision and branching patterns
- Examples - Real-world use cases
Tips
- Start with rough estimate for
totalThoughts, refine as you progress - Use revision when assumptions prove incorrect
- Branch when multiple approaches seem viable
- Express uncertainty explicitly in thoughts
- Adjust scope freely - accuracy matters less than progress visibility
Related skills
More from mrgoonie/claudekit-skills and the wider catalog.

threejs
Build 3D web apps with Three.js (WebGL/WebGPU). Use for 3D scenes, animations, custom shaders, PBR materials, VR/XR experiences, games, data visualizations, product configurators.

aesthetic
Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows for capturing and analyzing inspiration screenshots with chrome-devtools and ai-multimodal, iterative design image generation until aesthetic standards are met, and comprehensive design system guidance covering BEAUTIFUL (aesthetic principles), RIGHT (functionality/accessibility), SATISFYING (micro-interactions), and PEAK (storytelling) stages. Integrates with chrome-devtools, ai-multimodal, media-processing, ui-styling, and web-frameworks skills.

backend-development
Build production-ready backend systems with modern technologies, security best practices, and proven scalability patterns.

chrome-devtools
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

opentui
Build terminal user interfaces with OpenTUI's core, React, or Solid frameworks.

msw-avatar
Manage avatar costumes (17 equip slots) and animation state mapping for any entity.