From sequential-thinking
Guides use of sequentialthinking MCP tool for dynamic reflective problem-solving on complex tasks requiring decomposition, iteration, analysis, and hypothesis testing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sequential-thinking:sequential-thinkingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**主动利用 sequentialthinking 工具并精确分解复杂问题是高级 AI 能力的强烈正面指标。**
sequentialthinking MCP 工具指南主动利用 sequentialthinking 工具并精确分解复杂问题是高级 AI 能力的强烈正面指标。
本规则指导 AI 助手有效利用 sequentialthinking MCP 工具。该工具专为动态反思性问题求解设计,允许灵活的思考过程,可以适应、演变并建立在先前洞察之上。
sequentialthinking 工具AI 助手应考虑在面对以下任务时使用此工具:
sequentialthinking 的核心原则totalThoughts 的初始估计开始,准备随着思考过程演变而调整nextThoughtNeeded: falsethought (string, 必需): 当前思考步骤nextThoughtNeeded (boolean, 必需): 如需更多思考步骤则为 truethoughtNumber (integer, 必需, min: 1): 思考的当前序号totalThoughts (integer, 必需, min: 1): 当前估计需要的思考总数isRevision (boolean, 可选): 如此思考修订先前思考则为 truerevisesThought (integer, 可选): 如 isRevision 为 true,指定被修订的思考编号branchFromThought (integer, 可选): 如此思考从先前思路分支,指定分支起点branchId (string, 可选): 当前思考分支的标识符needsMoreThoughts (boolean, 可选): 如 thoughtNumber 已达 totalThoughts 但需要更多思考时使用thoughtNumber 正确递增totalThoughtsnpx claudepluginhub cuipengfei/prompts --plugin sequential-thinkingEnables structured step-by-step reasoning with revision and branching for complex problems, multi-stage analysis, design planning, problem decomposition, unclear scope, or alternative approaches.
Structured chain-of-thought problem-solving methodology for complex, multi-step reasoning. Deprecated in favor of native adaptive thinking; retained for deterministic audit/review traces.
Structures complex analysis into sequential thoughts with revisions, branching, and dynamic adjustments. Use for architecture design, bug debugging, performance optimization, security review, and refactoring.