tutor-skills

왜 쓰나요

핵심 기능

tutor-setup ingests PDFs, docs, HTML, and full codebases
Creates Obsidian vault with concept notes, wiki-links, a Map of Content, and practice questions
tutor runs 4-question rounds with graded answers and mastery badges
Separate modes: diagnostic, drill, hard-mode review
For codebases, traces architecture patterns and produces onboarding exercises

라이브 데모

실제 사용 모습

tutor-skill.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: tutor-skills

Turn a 400-page textbook PDF into a study vault you can actually use

👤 Students and self-learners ⏱ ~90 min intermediate

언제 쓸까: You have a textbook and would rather quiz yourself than re-read it.

사전 조건

Obsidian installed — obsidian.md — free
Claude Code CLI — Required for running the skills

흐름

Run tutor-setup

Use tutor-setup on ./textbook.pdf — build the vault at ~/vaults/calc.✓ 복사됨

→ Vault created with chapter notes, concept maps, and question bank
Start a study session

Use tutor. Start a diagnostic session on chapter 3.✓ 복사됨

→ 4 questions with grading and mastery update
Review weak areas

Show my weak concepts and drill them.✓ 복사됨

→ Targeted drill on lowest-mastery concepts

결과: A personal study vault plus a working retention loop.

함정

PDFs with poor OCR yield low-quality notes — Run OCR with a better tool first if the source is image-based

함께 쓰기: human-skill-tree-skill

Onboard to an unfamiliar codebase via guided quizzing

👤 New hires and contractors ⏱ ~120 min intermediate

언제 쓸까: You inherited a 50k-line codebase and reading it linearly isn't working.

흐름

Ingest the repo

Use tutor-setup on ~/src/acme-api. Trace the architecture and build onboarding exercises.✓ 복사됨

→ Vault with module map, architecture diagrams, and exercise questions
Run onboarding exercises

Use tutor. Start the onboarding track.✓ 복사됨

→ Exercises that force you to navigate the code to answer

결과: Faster ramp-up than reading docs cover-to-cover.

함정

Generated exercises too shallow — Ask tutor-setup to focus on specific modules rather than the whole repo

함께 쓰기: filesystem

조합

다른 MCP와 조합해 10배 효율

tutor-skill + human-skill-tree-skill

Document-centric (tutor) + dialogue-centric (human-skill-tree)

Use tutor on my textbook, then switch to human-skill-tree for Socratic discussion of the hard concepts.✓ 복사됨

tutor-skill + filesystem

Save progress summaries outside the vault for version control

Every week, snapshot my mastery report to ~/learning-log/.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
tutor-setup	source files (PDF/text/HTML/code)	Start of a new study topic	LLM tokens for extraction
tutor (quiz rounds)	vault + focus topic	Regular study sessions	Tokens per round
Diagnostic mode	topic	Start of topic or after time away	Tokens
Drill mode	weak concepts	Mid-study reinforcement	Tokens
Hard-mode review	mastered concepts	Confidence check before exam	Tokens

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: Setup can be heavy (20-100k tokens for a big PDF). Quizzes are light (2-5k per round).
금액: Free — skill is local. Obsidian is free.
팁: Split large textbooks by chapter for setup to keep ingestion manageable.

보안

권한, 시크릿, 파급범위

자격 증명 저장: No credentials — skill is prompts + local file ops

데이터 외부 송신: None — everything runs locally

If you ingest proprietary company docs, remember Claude reads them — follow your org's AI-content policy.

문제 해결

자주 발생하는 오류와 해결

Vault notes missing concepts from the source

Re-run tutor-setup with chapter-level focus; full-book in one pass can skim.

Questions feel too easy

Switch to hard-mode review or ask tutor for application-level questions.

Obsidian doesn't show the wiki-links

Check vault settings; enable backlinks and graph view plugins.

대안

tutor-skills 다른 것과 비교

대안	언제 쓰나	단점/장점
human-skill-tree-skill	You prefer dialogue-based learning without a document vault	Different modality — no persistent vault
Anki	You want pure SRS without the AI tutoring layer	Stronger SRS, no content generation