← Back to Skills Marketplace
18678837882

李继刚认知工具箱

by 18678837882 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
164
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install cognitive-tools
Description
整合李继刚原创的11个认知工具,实现逻辑分析、问题挖掘、抽象表达、多角度思考和公文写作等深度认知任务。
README (SKILL.md)

认知工具箱 (Cognitive Tools)

李继刚的11个AI认知工具 —— 提升AI思维深度

技能概述

李继刚(Prompt之神)的11个认知工具集,源自7本经典著作的本质精华提炼。 触发词:/思考 逻辑分析 问题之锤 抽象 多角度 定义 矩阵分析 类比 汉语新解 Prompt打分 知识探索 公文写作


11个工具详解

🔪 逻辑之刃

  • 用途:对文本进行庖丁解牛式的分析,提取命题并进行逻辑推导
  • 触发词逻辑分析 分析逻辑 用逻辑之刃
  • 适用场景:分析报告、拆解论证链、找逻辑漏洞

🔨 问题之锤

  • 用途:锤碎问题,找到问题背后的问题,一路敲下去直至第一问题显现
  • 触发词问题之锤 追问 深入挖掘 本质
  • 适用场景:决策分析、根因诊断、战略追问

🎋 抽象之梯

  • 用途:将文本在具象和抽象之间转换,让表达更细腻或更凝练
  • 触发词抽象 具象化 提升层次 抽象之梯
  • 适用场景:汇报提炼、战略解读、数据洞察

🪞 角度之镜

  • 用途:切换不同角度看待问题,综合所得,提出一个独特视角的切入解法
  • 触发词多角度 换个角度 角度之镜 视角分析
  • 适用场景:竞品分析、方案评估、局面研判

�茅 定义之矛

  • 用途:精准定义概念的本质,绕着它打转,一矛丢出,将它钉死在语义空间
  • 触发词定义 本质 概念界定 定义之矛
  • 适用场景:会议对齐、术语澄清、减少沟通歧义

🕸️ 矩阵之网

  • 用途:用两个维度、动态颗粒度,将课题肢解,狭隘地看全局
  • 触发词矩阵分析 多维分析 矩阵之网
  • 适用场景:市场分析、分类整理、多因素决策

🏹 类比之弓

  • 用途:抓住一个结构,同构外推到另一个用户更容易理解的场域
  • 触发词类比 打比方 类比之弓
  • 适用场景:向领导汇报、向客户解释、跨行业借鉴

📖 汉语新解

  • 用途:将一个汉语词汇进行全新角度的解释,语言风趣、一针见血
  • 触发词汉语新解 解释词汇 词汇新解
  • 适用场景:写作润色、表达创新、文化解读

⚖️ Prompt Judger

  • 用途:对Prompt进行评分(1-10)并提供改进建议
  • 触发词打分 Prompt评分 改进Prompt judger
  • 适用场景:优化OpenClaw自身技能、分析他人Prompt

🔍 知识探索专家

  • 用途:对一个知识点从来源、本质、发展三个维度深度探索
  • 触发词探索 知识探索 深度理解
  • 适用场景:学习新概念、理解新事物

📝 公文笔杆子

  • 用途:政府机关公文风格的写作,包括领导讲话稿、通知、报告等
  • 触发词公文 讲话稿 政府文件
  • 适用场景:行政文件、正式报告、官方文书

使用方法

单工具调用

直接说出工具名称,AI自动激活对应认知工具进行分析。

工具链组合(推荐用法)

问题之锤 → 角度之镜 → 逻辑之刃 → 矩阵之网

流程:用问题之锤深入挖掘本质 → 用角度之镜找到最佳观察角度 → 用逻辑之刃梳理因果关系 → 用矩阵之网多维肢解

示例对话

  • "用问题之锤分析:要不要扩产?"
  • "用逻辑之刃分析这份报告的论证链"
  • "用汉语新解解释'内卷'这个词"

技术说明

  • 所有工具基于李继刚原创Prompt,GitHub: github.com/lijigang/prompts
  • 以system prompt方式注入,无需外部API
  • 可与其他技能(deal-advisor、mbb-strategist等)串联使用

该技能整合自李继刚的11个认知工具,以提升AI思维深度为核心目标。

Usage Guidance
This skill is essentially a packaged set of system prompts — generally low-risk. Before installing, consider: 1) test a few triggers to confirm the outputs match your expectations and that references to external models/databases behave as intended; 2) if you plan to produce official government-style documents, review outputs for legal/ethical appropriateness (the "公文笔杆子" prompt enforces "政治正确" and strict formatting); 3) verify the claimed GitHub source if provenance/licensing matters to you (SKILL.md references github.com/lijigang/prompts); 4) ask the author to clarify ambiguous constraints such as "只输出数据库已有信息" so you know what internal data the skill may rely on. If you need guarantees about data handling or provenance, request explicit documentation from the publisher before use.
Capability Analysis
Type: OpenClaw Skill Name: cognitive-tools Version: 1.0.0 The 'cognitive-tools' skill bundle is a collection of system prompts designed to enhance an AI's analytical and creative capabilities through various frameworks like logical analysis, root cause diagnosis, and multi-perspective evaluation. The bundle consists entirely of Markdown documentation and prompt templates (e.g., SKILL.md, prompts/逻辑之刃.md, prompts/问题之锤.md) without any executable code, network requests, or sensitive data access. It is functionally safe and aligns perfectly with its stated purpose.
Capability Assessment
Purpose & Capability
Name/description (a toolbox of 11 cognitive/prompt templates) matches the provided files: a SKILL.md and 11 prompt files. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
All runtime instructions are prompt templates and usage guidance; they stay within cognitive/analysis/writing tasks. A few small ambiguities exist: some prompts reference model names (e.g., "Claude Sonnet") and one prompt (逻辑之刃) contains the constraint "只输出数据库已有信息" ("only output database-existing information") — it's unclear what "database" refers to in the agent context. Otherwise prompts do not instruct reading system files, contacting external endpoints, or exfiltrating data.
Install Mechanism
No install spec and no code files — instruction-only. This is the lowest-risk install mechanism and consistent with the skill's stated behavior.
Credentials
The skill declares no required environment variables, credentials, or config paths. The prompts do not require external API keys. Requested access is proportionate to an instruction-only prompt library.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request permanent system changes, nor does it indicate altering other skills or agent configuration beyond injecting system prompts at runtime.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install cognitive-tools
  3. After installation, invoke the skill by name or use /cognitive-tools
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of "认知工具箱 (Cognitive Tools)" skill, featuring 11 distinct AI cognitive tools distilled from seven classic books. - Enables users to activate tools like 逻辑之刃, 问题之锤, 抽象之梯, and others using simple trigger words for in-depth analysis, concept definition, multi-angle perspectives, and more. - Supports both single-tool invocation and recommended toolchain workflows to address complex problems systematically. - Incorporates original prompts by 李继刚 for each cognitive tool; seamlessly integrates with other skills and requires no external API.
Metadata
Slug cognitive-tools
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is 李继刚认知工具箱?

整合李继刚原创的11个认知工具,实现逻辑分析、问题挖掘、抽象表达、多角度思考和公文写作等深度认知任务。 It is an AI Agent Skill for Claude Code / OpenClaw, with 164 downloads so far.

How do I install 李继刚认知工具箱?

Run "/install cognitive-tools" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 李继刚认知工具箱 free?

Yes, 李继刚认知工具箱 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 李继刚认知工具箱 support?

李继刚认知工具箱 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 李继刚认知工具箱?

It is built and maintained by 18678837882 (@18678837882); the current version is v1.0.0.

💬 Comments