sequential-thinking

Structure multi-step reasoning with revision and branching for complex problems.

Updated Feb 27, 2026
One-click install
npx skills add https://github.com/haidonglethqb/CloudSchool --skill sequential-thinking-haidonglethqb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sequential-thinking
Source: https://github.com/haidonglethqb/CloudSchool/tree/main/.claude/skills/sequential-thinking
Command: npx skills add https://github.com/haidonglethqb/CloudSchool --skill sequential-thinking-haidonglethqb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Complex problems often require careful multi-step reasoning, context maintenance, and the ability to revise or branch ideas as new information emerges. This Skill provides a structured methodology to break down problems into manageable thoughts, track revisions, and explore alternative paths to convergence.

Core Features & Use Cases

  • Stepwise reasoning with dynamic adjustment of total thoughts (expand/contract/revise/branch) to match evolving understanding.
  • Revision and branch management to capture invalidated ideas and alternative solutions without losing context.
  • Hypothesis generation and verification loops to iteratively test ideas against evidence.
  • Explicit or implicit thinking modes to balance transparency with conciseness.
  • Detachable tooling via optional scripts (process-thought.js, format-thought.js) for deterministic validation, history tracking, and formatted outputs.
  • Ideal for complex debugging, architectural decision-making, root-cause analysis, and multi-step planning in education or engineering contexts.

Quick Start

Begin by outlining an initial set of thoughts for the problem, then iteratively revise and branch as new insights emerge to converge on a robust solution.

Frequently Asked Questions about sequential-thinking

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I break down complex problems for multi-step reasoning?

Decompose complex problems by outlining an initial set of thoughts, then iteratively revise and branch them as new insights emerge to converge on a robust solution. This methodology maintains context while allowing dynamic thought adjustment throughout the process.

What is the best way to track hypothesis testing and alternative branches during root-cause analysis?

Track hypothesis testing by using revision and branch management to capture invalidated ideas and explore alternative solutions without losing context. You can generate hypotheses and iteratively verify them against evidence through structured loops.

Can I use deterministic scripts for validation and formatted outputs in architectural decision-making?

Yes, you can leverage optional scripts like process-thought.js and format-thought.js for deterministic validation, history tracking, and formatted outputs. These scripts support architectural decision-making by providing structured, automated validation.

How do I adjust my total thoughts when new information emerges during problem decomposition?

Adjust total thoughts dynamically by expanding, contracting, or revising your initial outline to match your evolving understanding. This adaptive planning approach ensures your multi-step tasks remain aligned with new evidence.

Does this methodology support explicit and implicit thinking modes for complex debugging?

Yes, the methodology supports both explicit and implicit thinking modes to balance transparency with conciseness during complex debugging. This allows you to maintain clear context while choosing the appropriate level of reasoning visibility.