重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
sequential-thinking by secondsky/claude-skills
npx skills add https://github.com/secondsky/claude-skills --skill sequential-thinking通过具备修订和分支能力的迭代推理,实现结构化问题解决。
在以下情况使用 mcp__reasoning__sequentialthinking:
不适用于:简单查询、直接事实或单步任务。
MCP 工具 mcp__reasoning__sequentialthinking 接受以下参数:
thought (string):当前推理步骤nextThoughtNeeded (boolean):是否需要更多推理广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
thoughtNumber (integer):当前步骤编号(从 1 开始)totalThoughts (integer):预估所需的总步骤数isRevision (boolean):指示此步骤是否修订了先前的思考revisesThought (integer):正在重新考虑哪个思考步骤编号branchFromThought (integer):从哪个思考步骤编号进行分支branchId (string):此推理分支的标识符1. 从初始思考开始 (thoughtNumber: 1)
2. 对于每个步骤:
- 在 `thought` 中表达当前推理
- 通过 `totalThoughts` 预估剩余工作量(动态调整)
- 设置 `nextThoughtNeeded: true` 以继续
3. 当得出结论时,设置 `nextThoughtNeeded: false`
// 第一个思考
{
thought: "问题涉及优化数据库查询。需要首先识别瓶颈。",
thoughtNumber: 1,
totalThoughts: 5,
nextThoughtNeeded: true
}
// 第二个思考
{
thought: "分析查询模式发现用户获取中存在 N+1 问题。",
thoughtNumber: 2,
totalThoughts: 6, // 调整了范围
nextThoughtNeeded: true
}
// ... 继续直到完成
当您意识到先前的结论错误时:
{
thought: "重新考虑思考 #2:N+1 问题不是主要瓶颈 - 缺失索引才是。",
thoughtNumber: 5,
totalThoughts: 8,
nextThoughtNeeded: true,
isRevision: true,
revisesThought: 2
}
当探索替代方法时:
{
thought: "分支 A:如果我们用缓存而不是查询优化来解决这个问题会怎样?",
thoughtNumber: 6,
totalThoughts: 10,
nextThoughtNeeded: true,
branchFromThought: 3,
branchId: "caching-approach"
}
totalThoughts 进行粗略估计,随着进展进行优化每周安装量
74
代码仓库
GitHub 星标数
93
首次出现
2026 年 1 月 25 日
安全审计
已安装于
claude-code63
opencode59
codex59
gemini-cli59
cursor57
github-copilot55
Enables structured problem-solving through iterative reasoning with revision and branching capabilities.
Use mcp__reasoning__sequentialthinking when:
Don't use for : Simple queries, direct facts, or single-step tasks.
The MCP tool mcp__reasoning__sequentialthinking accepts these parameters:
thought (string): Current reasoning stepnextThoughtNeeded (boolean): Whether more reasoning is neededthoughtNumber (integer): Current step number (starts at 1)totalThoughts (integer): Estimated total steps neededisRevision (boolean): Indicates this revises previous thinkingrevisesThought (integer): Which thought number is being reconsideredbranchFromThought (integer): Thought number to branch frombranchId (string): Identifier for this reasoning branch1. 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`
// 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
When you realize an earlier conclusion was wrong:
{
thought: "Reconsidering thought #2: The N+1 problem isn't the main bottleneck - missing index is.",
thoughtNumber: 5,
totalThoughts: 8,
nextThoughtNeeded: true,
isRevision: true,
revisesThought: 2
}
When exploring alternative approaches:
{
thought: "Branch A: What if we solve this with caching instead of query optimization?",
thoughtNumber: 6,
totalThoughts: 10,
nextThoughtNeeded: true,
branchFromThought: 3,
branchId: "caching-approach"
}
totalThoughts, refine as you progressWeekly Installs
74
Repository
GitHub Stars
93
First Seen
Jan 25, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
claude-code63
opencode59
codex59
gemini-cli59
cursor57
github-copilot55
AI界面设计评审工具 - 全面评估UI/UX设计质量、检测AI生成痕迹与优化用户体验
58,500 周安装