Turns PDFs, codebases, or web sources into structured Obsidian study vaults with two auto-detected modes. Document mode extracts text from academic materials (mandates pdftotext to avoid token waste), maps topics to source pages, then generates concept notes with practice questions, comparison tables, and exam trap callouts. Codebase mode scans project markers like package.json or Cargo.toml, traces architecture and request flows, then builds onboarding notes per module with hands-on exercises for new developers. Both modes enforce wiki-linking, tag hierarchies, and a self-review checklist. Useful when you need to actually learn material rather than just highlight it, or when onboarding docs don't exist yet.

skills.sh installs
2.1K
GitHub stars
1.4K
last updated
Feb 28, 2026

Install

$ npx -y skills add bevibing/tutor-skills --skill tutor-setup --agent claude-code

Installs into .claude/skills of the current project.

Files

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:
    • package.json, pom.xml, build.gradle, Cargo.toml, go.mod, Makefile, *.sln, pyproject.toml, setup.py, Gemfile
  2. If any marker found → Codebase Mode
  3. If no marker found → Document Mode
  4. Tie-break: If .git/ is the sole indicator and no source code files (*.ts, *.py, *.java, *.go, *.rs, etc.) exist, default to Document Mode.
  5. 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

Phase D1: Source Discovery & Extraction

Sponsors

Details

Repository
github.com/bevibing/tutor-skills
License
MIT
First seen
Jun 11, 2026

More from bevibing/tutor-skills

All 2

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