Skip to main content
skill CX Codex

sequential-thinking — Claude Code skill: what it does, how to install

Breaks complex problems into iterative reasoning steps with dynamic scope and hypothesis branching. Built for architecture planning and deep debugging.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mrgoonie/claudekit-skills --skill sequential-thinking -a claude-code
Open on GitHub

What sequential-thinking does

This skill drives structured, step-by-step reasoning via the mcp__reasoning__sequentialthinking tool. Instead of jumping to conclusions, the agent records explicit thinking steps. It tracks progress using thoughtNumber and adjusts the anticipated scope through totalThoughts as new details emerge.

The tool workflow supports backtracking and branching. With isRevision and revisesThought, the model can reconsider previous flawed assumptions. If multiple viable paths exist, branchFromThought and branchId let it evaluate alternatives separately.

Running this on simple facts or single-step questions is pointless, as the extra tool calls add delay where a direct answer is needed.

What it helps with

  • decompose engineering problems with unclear initial scope
  • trace complex bugs through iterative hypothesis testing
  • explore alternative architecture branches without losing context
  • revise incorrect intermediate assumptions during multi-step analysis

Example prompts for the agent

  • Analyze our database bottleneck using sequential-thinking and explore alternative indexing strategies
  • Debug this memory leak step-by-step, revising previous thoughts if the profiling data contradicts them

How to install sequential-thinking

1Skills CLI (Vercel)

npx skills add mrgoonie/claudekit-skills --skill sequential-thinking -a claude-code

2Manually: put the files in place

~/.claude/skills/sequential-thinking/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/sequential-thinking/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about sequential-thinking

How to install sequential-thinking in Claude Code?

Run npx skills add mrgoonie/claudekit-skills --skill sequential-thinking -a claude-code. This installs the skill file into your Claude Code skills directory.

What does sequential-thinking do?

It guides the assistant through iterative problem-solving steps. The agent numbers each thought, dynamically updates total estimated steps, and branches into alternative approaches when needed.

When should you avoid using sequential-thinking?

Do not use it for simple lookups, direct factual answers, or one-step tasks. In straightforward prompts, the step-by-step MCP reasoning overhead slows down the response.

Source text

SKILL.md · MIT
---
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 step
- `nextThoughtNeeded` (boolean): Whether more reasoning is needed
- `thoughtNumber` (integer): Current step number (starts at 1)
- `totalThoughts` (integer): Estimated total steps needed

### Optional Parameters

- `isRevision` (boolean): Indicates this revises previous thinking
- `revisesThought` (integer): Which thought number is being reconsidered
- `branchFromThought` (integer): Thought number to branch from
- `branchId` (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

```typescript
// 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](references/advanced.md) - Revision and branching patterns
- [Examples](references/examples.md) - 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

© mrgoonie · MIT · mrgoonie/claudekit-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set20

backend-development A skill that walks your agent through API design, database schemas, auth and CI/CD. Useful when a backend starts from scratch or heads to production. CX Codex +1 2,300installs threejs A coding-agent skill that walks you through Three.js scenes, shaders and VR work. Useful when a project needs WebGL or WebGPU and you want the agent to know the API. CX Codex +1 1,200installs devops A skill for deploying and managing infrastructure across Cloudflare, Docker, GCP and Kubernetes. Useful when the agent has to ship a service or debug a cluster. CX Codex +1 987installs aesthetic A skill that walks your coding agent through interface design: reading other people's layouts, generating design images, and iterating until they hold up. CX Codex +1 714installs problem-solving A collection of structured creative thinking techniques to unblock agent reasoning. Helps find clean abstractions when conventional coding solutions hit a dead end. CX Codex +1 570installs debugging Enforces a disciplined debugging methodology that stops guesswork and requires fresh test proof before marking tasks done. CX Codex +1 569installs media-processing Runs FFmpeg and ImageMagick pipelines for video transcoding, audio extraction, image batch processing, and HLS streaming manifests. CX Codex +1 558installs ai-multimodal A skill that runs audio, video, image and PDF tasks through the Gemini API. Useful when you need a transcript, a screenshot read, or tables pulled out of a document. CX Codex +1 530installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor