sequential-thinking
Enables structured, iterative problem-solving with backtracking and branching capabilities.
Install
mkdir -p .claude/skills/sequential-thinking && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3" && unzip -o skill.zip -d .claude/skills/sequential-thinking && rm skill.zipInstalls to .claude/skills/sequential-thinking
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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.Key capabilities
- →Break complex problems into sequential steps
- →Revise previous conclusions based on new insights
- →Branch into alternative reasoning paths
- →Adjust total thought scope dynamically
- →Maintain reasoning context across multi-stage analysis
How it works
It uses an iterative reasoning tool that tracks thought numbers and total scope, allowing for branching and revision of the logic chain.
Inputs & outputs
When to use sequential-thinking
- →Decompose large technical requirements
- →Analyze complex architectural trade-offs
- →Explore multiple solution branches
- →Troubleshoot multi-stage logic bugs
About this skill
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
When not to use it
- →Simple factual lookups
- →Single-step tasks
- →Direct execution of commands without analysis
Limitations
- →Requires manual management of thought numbers
- →Overhead of structured thinking for simple tasks
How it compares
It provides a visible, revisable audit trail of the thought process compared to standard linear generation.
Compared to similar skills
sequential-thinking side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| sequential-thinking (this skill) | 136 | 9mo | No flags | Intermediate |
| ai-wrapper-product | 5 | 6mo | No flags | Intermediate |
| token-budget | 4 | 4mo | No flags | Intermediate |
| initializing-memory | 2 | 2mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by mrgoonie
View all by mrgoonie →You might also like
ai-wrapper-product
davila7
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.
token-budget
toonight
Manages token budget estimation and tracking to prevent context overflow
initializing-memory
letta-ai
Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory blocks.
A-Team
chemistrywow31
Start the A-Team Codex coordinator workflow for designing or restructuring teams
agentic-workflow-designer
Z3Prover
Conversational skill that interviews users to design new agentic workflows
multi-agent-patterns
georgekhananaev
Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures