Skip to content
Agentmart
Submit a tool

linear-algebra-learn

线性代数私教 — 从 0 带到「胜任」的有状态学习教练。13 模块 novice→competent，计算 + 几何直觉双线并进，按你的水平自适应出题批改、排复习。 触发词：「学线性代数」「教我线代」「继续学线代」「考我特征值」

Skill by swaylq

IndexedMIT★ 20
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/swaylq-linear-algebra-learn

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

线性代数私教 — 从 0 带到「胜任」的有状态学习教练。13 模块 novice→competent，计算 + 几何直觉双线并进，按你的水平自适应出题批改、排复习。 触发词：「学线性代数」「教我线代」「继续学线代」「考我特征值」

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 3

  • 3blue1brown.com · found in code
  • codeload.github.com · found in install command
  • ocw.mit.edu · found in code

Files it touches

  • ~/.claude/skills/linear-algebra-learn

Tools it pre-approves 4

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Write,
  • Edit,
  • Bash

What's inside

Skill name
linear-algebra-learn
Description
线性代数私教 — 从 0 带到「胜任」的有状态学习教练。13 模块 novice→competent，计算 + 几何直觉双线并进，按你的水平自适应出题批改、排复习。 触发词：「学线性代数」「教我线代」「继续学线代」「考我特征值」
License
MIT
Allowed tools
Read,, Write,, Edit,, Bash
Instructions
30 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves any shell command

Files (8)

  • README.md
  • SKILL.md
  • curriculum.json
  • curriculum.md
  • learner-state.example.json
  • meta.json
  • pedagogy.md · references/
  • notes.md · references/research/

SKILL.md (first lines)

# 线性代数 · 私教

> 从向量和消元，走到特征值、对角化、SVD——到能独立从一组数据走到主成分并解释每步几何意义。计算我能批，几何直觉我帮你建。

## 激活规则
收到学线代相关请求时，先读 `learner-state.json`，再按【开课协议】教。

## 开课协议
1. 读档（首次诊断：会不会解方程组 / 懂不懂向量几何 / 学没学过微积分 → 定起点，写 placement）。
2. 选焦点：到期复习 → 下一模块 → 补薄弱。
3. 一次一模块。

## 教学法协议
- 新概念：先用 3Blue1Brown 式**几何直觉**建图像 → worked example 手算一遍 → 撤支架 → 独立算 → numpy 验证。
- 计算技能：直接出 drill 批改。
- 记忆（秩-零化度、行列式几何义、特征值定义）：检索练习进 `spaced_queue`。
- 坚持「算完要能解释几何意义」，不许只会机械消元。

## 评估与档案更新
出题 → 批改 → 调 `tools/learner_state.py`（`update_module` / `record_exercise` / `schedule_review` / `bump_streak`）。

## 诚实边界
- 天花板「胜任」：能独立做特征分解 / SVD / 最小二乘并解释；抽象证明（Axler 风格）、数值稳定性、大规模计算属精通 / 工程区，点到为止。
- 我能批计算和几何直觉；**严格证明的逻辑漏洞**建议对照 MIT 18.06 答案或找助教。
- 概念核心不衰减；工具（numpy / 具体库）会变，`update 私教 linear-algebra` 刷。

## 课程大纲
见 [`curriculum.md`](curriculum.md)（由 `curriculum.json` 渲染，勿手改）。

From swaylq/sijiao-skill, MIT.

More from swaylq/sijiao-skill

Signals

Stars
20
Forks
2
Open issues
1
Last commit (this folder)
Jun 16, 2026 (4 months ago)
Last release
Aug 16, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/swaylq/sijiao-skill
Website
swaylq.github.io/sijiao-skill/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from swaylq

Cite this page

linear-algebra-learn skill. Agent Mart. https://agentmart.dev/skills/swaylq-linear-algebra-learn (last updated 2026-10-24)