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 →
npx skills add https://github.com/hexbee/hello-skills --skill learning-first-principles学习的本质是内在驱动而非外部灌输:
| 层级 | 反模式(应避免) | 正向模式(应追求) |
|---|---|---|
| 学习观 | 依赖辅导/外部输入 | 自我驱动学习 |
| 方法论 | 耗时/机械重复 | 归纳与总结 |
| 处理方式 | 机械抄录 | 自我输出 |
| 输出形式 | 简单重复 | 表达重构 |
| 表达方式 | 形式化/模板化 | 逻辑驱动 |
| 理解程度 | 停留在理论 | 实践验证 |
当用户提供学习内容、方法或计划时,从以下维度进行分析:
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
用户输入:我想学习 Python,报名了培训班,每天上课2小时
分析输出:
诊断:
- 依赖外部输入(培训班)而非自我驱动学习
- 被动接收而非主动探索
改进建议:
1. 首先设定具体项目目标(例如:办公自动化脚本)
2. 用项目驱动学习,培训班作为补充资源
3. 每天花1小时做项目,0.5小时针对性听课
效率评估:
- 当前:低效(被动学习,遗忘率高)
- 优化后:高效(主动构建,可迁移性强)
每周安装量
50
代码仓库
首次出现
2026年1月21日
安全审计
安装于
gemini-cli40
opencode40
codex39
cursor38
github-copilot36
claude-code36
The essence of learning is internal drive rather than external infusion:
| Level | Anti-pattern (Avoid) | Positive Pattern (Pursue) |
|---|---|---|
| Learning View | Relying on tutoring/external input | Self-learning driven |
| Methodology | Time-consuming/mechanical repetition | Induction & summary |
| Processing | Mechanical copying | Self-output |
| Output | Simple repetition | Expression restructuring |
| Expression | Formal/template-based | Logic-driven |
| Understanding | Stopping at theory | Practice verification |
When users provide learning content, methods, or plans, analyze from these dimensions:
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)
Weekly Installs
50
Repository
First Seen
Jan 21, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli40
opencode40
codex39
cursor38
github-copilot36
claude-code36
OpenContext AI助手持久化记忆工具:跨会话上下文管理,减少重复解释
10,500 周安装