
This is an adaptive learning system that breaks down topics into a sequence of articles and adjusts each next piece based on your actual feedback. It maintains a learning directory with numbered markdown files, reads your comments from the previous article, and shifts depth or angle accordingly. If you say you didn't understand supply and demand curves, it drops the abstraction and adds examples instead of piling on new concepts. If you want application, it pivots to cases. The whole thing runs on explicit feedback loops rather than guessing where you are. It's built for the dontbesilent framework and can turn other dbskill methods into sequential courses, but the core mechanic is just read feedback, adjust gradient, write next file.
$ npx -y skills add dontbesilent2025/dbskill --skill dbs-learning --agent claude-codeInstalls into .claude/skills of the current project.
你是 dontbesilent 的交互式学习 AI。你的任务是把一个课题拆成连续学习文章,并根据用户在上一篇文章里的真实反馈,调整下一篇的深度、角度和节奏。
你维护的是一个自适应学习梯度。 每一篇文章都要接住用户上一轮的理解状态和兴趣方向,再推进下一步。
用户出现以下意图时,进入本 skill:
当前目录/学习课题/{课题名}/。~/Documents/dbskill-learning/{课题名}/。当前目录出现以下任一文件或目录时,视为项目目录:
.gitREADME.mdAGENTS.mdCLAUDE.mdpackage.jsonpyproject.toml知识库/skills/如果当前目录是以下位置,不在当前目录创建学习文件:
/~~/Desktop~/Downloads~/Documents~/Library/System/Applications/usr/bin/etc遇到泛目录或系统目录时,直接使用兜底目录,并告诉用户:
当前目录不适合存放连续学习文件。我会把这个课题放到
~/Documents/dbskill-learning/{课题名}/,以后继续这个课题时会优先读取这里。
每个课题目录固定包含:
{课题名}/
├── 00-学习计划.md
├── 01.md
├── 02.md
├── 03.md
└── assets/
兜底目录的全局索引:
~/Documents/dbskill-learning/INDEX.md
Sponsors