npx skills add https://github.com/roundtable02/tutor-skills --skill tutor基于测验的导师,在概念层面追踪用户已知和未知的内容。目标是帮助用户通过问题发现他们的盲区。
StudyVault/
├── *dashboard* ← 概览:熟练度表格 + 统计数据
└── concepts/
├── {area-name}.md ← 按领域的概念追踪(尝试次数、状态、错误笔记)
└── ...
从用户消息中检测用户语言 → {LANG}。所有输出和文件内容均使用 {LANG}。
**/StudyVault/**/StudyVault/*dashboard* 以找到仪表板广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
如果不存在 StudyVault,则通知用户并停止。
强制要求 : 使用 AskUserQuestion 让用户选择要做什么。分析仪表板以构建基于上下文的选项,然后呈现给用户。
读取仪表板熟练度表格,并根据当前状态构建选项:
将这些选项作为 AskUserQuestion 呈现,标题为"会话",并附上简洁的描述,说明每个选项针对哪些领域。用户必须在继续之前进行选择。
concepts/{area}.md 以查找 🔴 未解决的概念 — 在新的上下文中重新表述这些问题(不要重复相同的问题)references/quiz-rules.md 的规则精心设计恰好 4 个问题关键 : 在构建任何问题之前,先阅读 references/quiz-rules.md。不允许提供任何提示。
使用 AskUserQuestion:
concepts/{area}.md)对于每个已回答的问题:
### 오답 메모(或本地化等效标题)下添加错误笔记表格格式:
| 概念 | 尝试次数 | 正确次数 | 最后测试日期 | 状态 |
|---------|----------|---------|-------------|--------|
| 概念名称 | 2 | 1 | 2026-02-24 | 🔴 |
错误笔记格式(仅针对错误答案):
### 错误笔记
**概念名称**
- 混淆点:用户混淆了什么
- 关键点:正确的理解是什么
仪表板保持紧凑 — 不包含会话日志,不包含每个问题的详细信息。
当不存在仪表板时创建。文件名根据 {LANG} 本地化。英文示例:
# 学习仪表板
> 基于概念的元认知追踪。详情请见链接文件。
---
## 按领域熟练度
| 领域 | 正确 | 错误 | 正确率 | 等级 | 详情 |
|------|---------|-------|------|-------|---------|
(每个章节一行,最后一列 = [[concepts/{area}]] 链接)
| **总计** | **0** | **0** | **-** | ⬜ 未测量 | |
> 🟥 薄弱 (0-39%) · 🟨 一般 (40-69%) · 🟩 良好 (70-89%) · 🟦 精通 (90-100%) · ⬜ 未测量
---
## 统计数据
- **总问题数**: 0
- **累计正确率**: -
- **未解决概念**: 0
- **已解决概念**: 0
- **最薄弱领域**: -
- **最擅长领域**: -
在首次提问某个领域的问题时创建。示例:
# {领域名称} — 概念追踪器
| 概念 | 尝试次数 | 正确次数 | 最后测试日期 | 状态 |
|---------|----------|---------|-------------|--------|
### 错误笔记
(在概念被答错时添加)
references/quiz-rules.md每周安装次数
510
仓库
GitHub 星标
530
首次出现
2026年2月24日
安全审计
安装于
codex504
opencode502
gemini-cli495
kimi-cli493
cursor493
github-copilot493
Quiz-based tutor that tracks what the user knows and doesn't know at the concept level. The goal is helping users discover their blind spots through questions.
StudyVault/
├── *dashboard* ← Compact overview: proficiency table + stats
└── concepts/
├── {area-name}.md ← Per-area concept tracking (attempts, status, error notes)
└── ...
Detect user's language from their message → {LANG}. All output and file content in {LANG}.
**/StudyVault/ in project**/StudyVault/*dashboard* to find dashboardIf no StudyVault exists, inform user and stop.
MANDATORY : Use AskUserQuestion to let the user choose what to do. Analyze the dashboard to build context-aware options, then present them.
Read the dashboard proficiency table and build options based on current state:
Present these as an AskUserQuestion with header "Session" and concise descriptions showing which areas each option targets. The user MUST select before proceeding.
concepts/{area}.md to find 🔴 unresolved concepts — rephrase these in new contexts (don't repeat the same question)references/quiz-rules.mdCRITICAL : Read references/quiz-rules.md before crafting ANY question. Zero hints allowed.
Use AskUserQuestion:
concepts/{area}.md)For each question answered:
### 오답 메모 (or localized equivalent)Table format:
| Concept | Attempts | Correct | Last Tested | Status |
|---------|----------|---------|-------------|--------|
| concept name | 2 | 1 | 2026-02-24 | 🔴 |
Error notes format (only for wrong answers):
### Error Notes
**concept name**
- Confusion: what the user mixed up
- Key point: the correct understanding
Dashboard stays compact — no session logs, no per-question details.
Create when no dashboard exists. Filename localized to {LANG}. Example in English:
# Learning Dashboard
> Concept-based metacognition tracking. See linked files for details.
---
## Proficiency by Area
| Area | Correct | Wrong | Rate | Level | Details |
|------|---------|-------|------|-------|---------|
(one row per section, last column = [[concepts/{area}]] link)
| **Total** | **0** | **0** | **-** | ⬜ Unmeasured | |
> 🟥 Weak (0-39%) · 🟨 Fair (40-69%) · 🟩 Good (70-89%) · 🟦 Mastered (90-100%) · ⬜ Unmeasured
---
## Stats
- **Total Questions**: 0
- **Cumulative Rate**: -
- **Unresolved Concepts**: 0
- **Resolved Concepts**: 0
- **Weakest Area**: -
- **Strongest Area**: -
Create per area when first question is asked. Example:
# {Area Name} — Concept Tracker
| Concept | Attempts | Correct | Last Tested | Status |
|---------|----------|---------|-------------|--------|
### Error Notes
(added as concepts are missed)
references/quiz-rules.md before creating questionsWeekly Installs
510
Repository
GitHub Stars
530
First Seen
Feb 24, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex504
opencode502
gemini-cli495
kimi-cli493
cursor493
github-copilot493
头脑风暴技能:AI协作设计流程,将创意转化为完整规范与实施计划
79,800 周安装