Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问clear审计未展示

learning-first-principles学习第一原则

Agent Skill

learning-first-principles 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 Codex、Claude、Cursor、Gemini CLI 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。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

1,117

周安装

48

GitHub Stars

公开资料未说明

下载量

392
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:learning-first-principles(学习第一原则)
来源仓库:https://github.com/hexbee/hello-skills
仓库路径:skills/learning-first-principles
安装命令:
npx skills add hexbee/hello-skills --skill "learning-first-principles"
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 hexbee/hello-skills --skill "learning-first-principles"

简介

学习第一原则用于记录任务执行中的错误、用户纠正和最佳实践,帮助 Agent 持续优化能力。

  • 适用于 Codex、Claude、Cursor、Gemini CLI 等宿主环境。
  • 通过 GitHub 安装,使用 npx skills add hexbee/hello-skills --skill "learning-first-principles" 命令。
  • 安装前需确认权限范围、维护状态,并注意是否会触发联网或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

name
learning-first-principles
description
A cognitive framework based on learning first principles, providing learning method diagnosis, efficiency assessment, and optimization advice. Use when: (1) Diagnosing if current learning methods align with first principles, (2) Evaluating learning plan efficiency and time investment, (3) Analyzing learning behavior problems and providing improvement suggestions, (4) Determining if learning content is worth the time investment. Core principle chain: Self-learning → Induction → Self-output → Expression restructuring → Logical understanding → Practice.

Learning First Principles Analysis

Core Principle

The essence of learning is internal drive rather than external infusion:

LevelAnti-pattern (Avoid)Positive Pattern (Pursue)
Learning ViewRelying on tutoring/external inputSelf-learning driven
MethodologyTime-consuming/mechanical repetitionInduction & summary
ProcessingMechanical copyingSelf-output
OutputSimple repetitionExpression restructuring
ExpressionFormal/template-basedLogic-driven
UnderstandingStopping at theoryPractice verification

Analysis Framework

When users provide learning content, methods, or plans, analyze from these dimensions:

1. Self-learning Drive

  • Diagnosis: Relying on external push (tutoring, supervision)?
  • Action: Transform into self-driven exploration goals

2. Induction & Summary

  • Diagnosis: "Killing time" rather than "thinking"?
  • Action: Extract core, transferable patterns

3. Self-output

  • Diagnosis: Mechanically copying?
  • Action: Restate in your own words

4. Expression Restructuring

  • Diagnosis: Simply repeating textbook wording?
  • Action: Reorganize knowledge from new angles and frameworks

5. Logic-driven

  • Diagnosis: Applying templates/forms blindly?
  • Action: Trace causal chains, understand why

6. Practice Verification

  • Diagnosis: Stopping at theoretical understanding?
  • Action: Design minimal verification experiments

Output Format

Problem Diagnosis

  • Point out specific behaviors violating first principles
  • Use principle chain to explain problem roots

Improvement Suggestions

  • Provide 1-3 immediately actionable steps
  • Each action corresponds to a principle level

Efficiency Assessment

  • Estimate time ROI of current methods
  • Provide expected efficiency improvement after optimization

Usage Example

User Input: I want to learn Python, signed up for a training class, 2 hours of class daily

Analysis Output:

Diagnosis:
- Relying on external input (training class) instead of self-learning driven
- Passive reception instead of active exploration

Improvement Suggestions:
1. First set a specific project goal (e.g., office automation script)
2. Use projects to drive learning, training class as supplementary resource
3. Spend 1 hour daily on projects, 0.5 hours on targeted lectures

Efficiency Assessment:
- Current: Low (passive learning, high forgetting rate)
- Optimized: High (active construction, transferable)

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

Claude Code

29.59%
按下载量换算116

Gemini CLI

24.76%
按下载量换算97

Antigravity

17.85%
按下载量换算70

windsurf

12.54%
按下载量换算49

OpenCode

7.74%
按下载量换算30

Codex

4.3%
按下载量换算17

安全审计

暂无安全审计结果可展示。

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

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