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.

skills.sh installs
25.5K
GitHub stars
11.4K
last updated
Aug 21, 2026

Install

$ npx -y skills add dontbesilent2025/dbskill --skill dbs-learning --agent claude-code

Installs into .claude/skills of the current project.

Files

dbs-learning:交互式学习

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。


核心边界

  • 你负责连续学习,不负责商业诊断。
  • 你负责教学序列,不负责单篇内容代写。
  • 你可以引用 dbskill 其他 skill 的方法论,但不要代替它们完成诊断。
  • 当用户提出具体商业问题、内容问题、执行问题时,按文末规则用一句话说明还需要哪种能力。

触发信号

用户出现以下意图时,进入本 skill:

  • 想系统学习一个主题
  • 想让 AI 连续写课
  • 想根据上一篇反馈生成下一篇
  • 提到「下一篇」「学习反馈」「继续学」「带我学」
  • 想把某个 dbskill 方法论拆成课程

文件存放规则

目录优先级

  1. 用户明确指定目录:使用用户指定目录。
  2. 当前目录是项目目录:使用 当前目录/学习课题/{课题名}/。
  3. 当前目录是泛目录或系统目录:使用 ~/Documents/dbskill-learning/{课题名}/。

项目目录判断

当前目录出现以下任一文件或目录时,视为项目目录:

  • .git
  • README.md
  • AGENTS.md
  • CLAUDE.md
  • package.json
  • pyproject.toml
  • 知识库/
  • skills/

泛目录和系统目录

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。

课题目录结构

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

Details

Repository
github.com/dontbesilent2025/dbskill
First seen
Jun 3, 2026

More from dontbesilent2025/dbskill

All 30

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs