Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问clear审计未展示

sequential-thinking顺序思维

Agent Skill

sequential-thinking 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

499

周安装

20

GitHub Stars

公开资料未说明

下载量

162
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sequential-thinking(顺序思维)
来源仓库:https://github.com/huynguyen03dev/opencode-setup
仓库路径:skills/sequential-thinking
安装命令:
npx skills add huynguyen03dev/opencode-setup --skill "sequential-thinking"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add huynguyen03dev/opencode-setup --skill "sequential-thinking"

简介

发现并安装 AI 代理的技能。

  • 适用于在 Codex、Claude、Cursor、Gemini CLI 等宿主中扩展功能边界的场景。
  • 通过标准化命令快速添加新技能,无需手动克隆仓库。
  • 安装前需确认宿主支持 npx skills add 机制,并检查网络连接状态。
  • sequential-thinking 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
sequential-thinking
description
Dynamic problem-solving through structured sequential thoughts. Use when breaking down complex problems, planning multi-step solutions, analyzing ambiguous requirements, debugging intricate issues, exploring design alternatives, or tackling problems where the full scope is unclear. Enables thought revision, branching, and iterative refinement.

Sequential Thinking

Overview

This skill provides structured sequential thinking for complex problem-solving through a dynamic, reflective thought process. Each thought can build on, question, or revise previous insights as understanding deepens.

When to Use

  • Breaking down complex problems into manageable steps
  • Planning and design with room for revision
  • Analysis that might need course correction
  • Problems where full scope is unclear initially
  • Multi-step solutions requiring maintained context
  • Filtering irrelevant information from complex scenarios
  • Debugging intricate issues requiring systematic exploration

Script Location

The script is located at: ~/.config/opencode/skills/sequential-thinking/scripts/sequential-thinking.ts

Use $SKILL_DIR or the full path when invoking from any directory.

Core Workflow

1. Initialize Thinking

Start a thinking sequence by estimating total thoughts needed:

bun ~/.config/opencode/skills/sequential-thinking/scripts/sequential-thinking.ts sequentialthinking \
  --thought "Initial analysis of the problem..." \
  --thought-number 1 \
  --total-thoughts 5 \
  --next-thought-needed true

2. Continue Sequence

Build on previous thoughts, adjusting estimates as needed:

bun ~/.config/opencode/skills/sequential-thinking/scripts/sequential-thinking.ts sequentialthinking \
  --thought "Building on insight from step 1..." \
  --thought-number 2 \
  --total-thoughts 5 \
  --next-thought-needed true

3. Revise Previous Thinking

When reconsidering earlier conclusions:

bun ~/.config/opencode/skills/sequential-thinking/scripts/sequential-thinking.ts sequentialthinking \
  --thought "Reconsidering step 2, I realize..." \
  --thought-number 4 \
  --total-thoughts 6 \
  --is-revision true \
  --revises-thought 2 \
  --next-thought-needed true

4. Branch Exploration

Explore alternative approaches:

bun ~/.config/opencode/skills/sequential-thinking/scripts/sequential-thinking.ts sequentialthinking \
  --thought "Alternative approach from step 3..." \
  --thought-number 5 \
  --total-thoughts 7 \
  --branch-from-thought 3 \
  --branch-id "alternative-approach" \
  --next-thought-needed true

5. Complete Thinking

Conclude when solution is verified:

bun ~/.config/opencode/skills/sequential-thinking/scripts/sequential-thinking.ts sequentialthinking \
  --thought "Final verified conclusion..." \
  --thought-number 6 \
  --total-thoughts 6 \
  --next-thought-needed false

Key Features

  • Adjustable estimates: Modify totalThoughts up/down as understanding evolves
  • Thought revision: Mark thoughts as revisions with --is-revision and --revises-thought
  • Branching: Explore alternatives with --branch-from-thought and --branch-id
  • Non-linear thinking: Branch or backtrack as needed
  • Hypothesis verification: Generate and verify solution hypotheses iteratively

Parameters Reference

ParameterRequiredDescription
--thoughtYesCurrent thinking step content
--thought-numberYesCurrent position in sequence (1-based)
--total-thoughtsYesEstimated total thoughts (adjustable)
--next-thought-neededYestrue to continue, false to conclude
--is-revisionNotrue if revising previous thinking
--revises-thoughtNoWhich thought number being revised
--branch-from-thoughtNoBranching point thought number
--branch-idNoIdentifier for the branch
--needs-more-thoughtsNoSignal more thoughts needed

Output Formats

Control output with --output flag:

  • text (default): Human-readable text
  • json: Structured JSON
  • markdown: Markdown formatted
  • raw: Raw response data

Resources

scripts/

  • sequential-thinking.ts - MCP server wrapper for sequential thinking (requires Bun runtime)

references/

  • thinking-patterns.md - Common thinking patterns and examples for various problem types

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenCode

26.35%
按下载量换算43

Claude Code

23.22%
按下载量换算38

Antigravity

15.53%
按下载量换算25

windsurf

12.05%
按下载量换算20

Codex

7.87%
按下载量换算13

Gemini CLI

3.49%
按下载量换算6

安全审计

暂无安全审计结果可展示。

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills