‹ 首页

tutor-setup

@bevibing · 收录于 1 周前 · 上游提交 4 个月前

Transforms knowledge sources into an Obsidian StudyVault. Two modes: (1) Document Mode — PDF/text/web sources → study notes with practice questions. (2) Codebase Mode — source code project → onboarding vault for new developers. Mode is auto-detected based on project markers in CWD.

适合你,如果常需将资料整理为带练习题的笔记或为新开发者准备代码库入门文档

/ 下载安装
tutor-setup.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add bevibing/tutor-skills/tutor-setup
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- bevibing/tutor-skills/tutor-setup
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify bevibing/tutor-skills/tutor-setup
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
1021GitHub stars
~1.6K最小装载
~5.9K含声明引用
~5.9K文本包总量
镜像托管

怎么用

商店整理自技能原文 · 版本 397110c · 表述以原文为准
它做什么

将知识源(PDF、文本、网页、代码项目)自动转换为 Obsidian 学习库。文档模式生成带练习题的学习笔记;代码库模式为新开发者生成项目入门指南。

什么时候触发

当你在当前工作目录下运行此技能时触发。它会自动检测目录中是否存在项目标记文件(如 package.json、pom.xml 等),从而决定使用文档模式或代码库模式。

装好后可以这样说
触发文档模式,自动扫描并转换 PDF 文件。
触发代码库模式,分析项目结构并生成入门指南。
使用 WebFetch 获取网页内容,然后生成笔记。
技能原文 SKILL.md作者撰写 · MIT · 397110c

Tutor Setup — Knowledge to Obsidian StudyVault

CWD Boundary Rule (ALL MODES)
NEVER access files outside the current working directory (CWD). All source scanning, reading, and vault output MUST stay within CWD and its subdirectories. If the user provides an external path, ask them to copy the files into CWD first.
Mode Detection

On invocation, detect mode automatically:

  1. Check for project markers in CWD:
  2. package.json, pom.xml, build.gradle, Cargo.toml, go.mod, Makefile, *.sln, pyproject.toml, setup.py, Gemfile
  3. If any marker foundCodebase Mode
  4. If no marker foundDocument Mode
  5. Tie-break: If .git/ is the sole indicator and no source code files (*.ts, *.py, *.java, *.go, *.rs, etc.) exist, default to Document Mode.
  6. Announce detected mode and ask user to confirm or override.

Document Mode
Transforms knowledge sources (PDF, text, web, epub) into study notes. Templates: [templates.md](references/templates.md)
Phase D1: Source Discovery & Extraction
  1. Auto-scan CWD for **/*.pdf, **/*.txt, **/*.md, **/*.html, **/*.epub (exclude node_modules/, .git/, dist/, build/, StudyVault/). Present for user confirmation.
  2. Extract text (MANDATORY tools):
  3. PDF → pdftotext CLI ONLY (run via Bash tool). NEVER use the Read tool directly on PDF files — it renders pages as images and wastes 10-50x more tokens. Convert to .txt first, then Read the .txt file. ```bash pdftotext "source.pdf" "/tmp/source.txt" ```
  4. If pdftotext is not installed, install it first: brew install poppler (macOS) or apt-get install poppler-utils (Linux).
  5. URL → WebFetch
  6. Other formats (.md, .txt, .html) → Read directly.
  7. Read extracted .txt files — understand scope, structure, depth. Work exclusively from the converted text, never from the raw PDF.
  8. Source Content Mapping (MANDATORY for multi-file sources):
  9. Read cover page + TOC + 3+ sample pages from middle/end for EVERY source file
  10. NEVER assume content from filename — file numbering often ≠ chapter numbering
  11. Build verified mapping: { source_file → actual_topics → page_ranges }
  12. Flag non-academic files and missing sources
  13. Present mapping to user for verification before proceeding
Phase D2: Content Analysis
  1. Identify topic hierarchy — sections, chapters, domain divisions.
  2. Separate concept content vs practice questions.
  3. Map dependencies between topics.
  4. Identify key patterns — comparisons, decision trees, formulas.
  5. Full topic checklist (MANDATORY) — every topic/subtopic listed. Drives all subsequent phases.
Equal Depth Rule: Even a briefly mentioned subtopic MUST get a full dedicated note supplemented with textbook-level knowledge.
  1. Classification completeness: When source enumerates categories ("3 types of X"), every member gets a dedicated note. Scan for: "types of", "N가지", "categories", "there are N".
  2. Source-to-note cross-verification (MANDATORY): Record which source file(s) and page range(s) cover each topic. Flag untraceable topics as "source not available".
Phase D3: Tag Standard

Define tag vocabulary before creating notes:

  • Format: English, lowercase, kebab-case (e.g., #data-hazard)
  • Hierarchy: top-level → domain → detail → technique → note-type
  • Registry: Only registered tags allowed. Detail tags co-attach parent domain tag.
Phase D4: Vault Structure

Create StudyVault/ with numbered folders per [templates.md](references/templates.md). Group 3-5 related concepts per file.

Phase D5: Dashboard Creation

Create 00-Dashboard/: MOC, Quick Reference, Exam Traps. See [templates.md](references/templates.md).

  • MOC: Topic Map + Practice Notes + Study Tools + Tag Index (with rules) + Weak Areas (with links) + Non-core Topic Policy
  • Quick Reference: every heading includes → [[Concept Note]] link; all key formulas
  • Exam Traps: per-topic trap points in fold callouts, linked to concept notes
Phase D6: Concept Notes

Per [templates.md](references/templates.md). Key rules:

  • YAML frontmatter: source_pdf, part, keywords (MANDATORY)
  • source_pdf MUST match verified Phase D1 mapping — never guess from filename
  • If unavailable: source_pdf: 원문 미보유
  • [[wiki-links]], callouts ([!tip], [!important], [!warning]), comparison tables > prose
  • ASCII diagrams for processes/flows/sequences
  • Simplification-with-exceptions: general statements must note edge cases
Phase D7: Practice Questions

Per [templates.md](references/templates.md). Key rules:

  • Every topic folder MUST have a practice file (8+ questions)
  • Active recall: answers use > [!answer]- 정답 보기 fold callout
  • Patterns use > [!hint]- / > [!summary]- fold callouts
  • Question type diversity: ≥60% recall, ≥20% application, ≥2 analysis per file
  • ## Related Concepts with [[wiki-links]]
Phase D8: Interlinking
  1. ## Related Notes on every concept note
  2. MOC links to every concept + practice note
  3. Cross-link concept ↔ practice; siblings reference each other
  4. Quick Reference sections → [[Concept Note]] links
  5. Weak Areas → relevant note + Exam Traps; Exam Traps → concept notes
Phase D9: Self-Review (MANDATORY)

Verify against [quality-checklist.md](references/quality-checklist.md) Document Mode section. Fix and re-verify until all checks pass.


Codebase Mode
Generates a new-developer onboarding StudyVault from a source code project. Full workflow: [codebase-workflow.md](references/codebase-workflow.md) Templates: [codebase-templates.md](references/codebase-templates.md)
Phase Summary

| Phase | Name | Key Action | |-------|------|------------| | C1 | Project Exploration | Scan files, detect tech stack, read entry points, map directory layout | | C2 | Architecture Analysis | Identify patterns, trace request flow, map module boundaries and data flow | | C3 | Tag Standard | Define #arch-*, #module-*, #pattern-*, #api-* tag registry | | C4 | Vault Structure | Create StudyVault/ with Dashboard, Architecture, per-module, DevOps, Exercises folders | | C5 | Dashboard | MOC (Module Map + API Surface + Getting Started + Onboarding Path) + Quick Reference | | C6 | Module Notes | Per-module notes: Purpose, Key Files, Public Interface, Internal Flow, Dependencies | | C7 | Onboarding Exercises | Code reading, configuration, debugging, extension exercises (5+ per major module) | | C8 | Interlinking | Cross-link modules, architecture ↔ implementations, exercises ↔ modules | | C9 | Self-Review | Verify against [quality-checklist.md](references/quality-checklist.md) Codebase Mode section |

See [codebase-workflow.md](references/codebase-workflow.md) for detailed per-phase instructions.


Language
  • Match source material language (Korean → Korean notes, etc.)
  • Tags/keywords: ALWAYS English
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。