tutor-setup

Name: tutor-setup
Author: bevibing

98installs89forks

How to install tutor-setup?

bevibing/tutor-skills/tutor-setup

$npx -y skills add bevibing/tutor-skills --skill tutor-setup

Installs into the current project.

Summary

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 CW

Files · 1

View on GitHub

SKILL.md

1	# Tutor Setup — Knowledge to Obsidian StudyVault
2
3	## CWD Boundary Rule (ALL MODES)
4
5	> NEVER access files outside the current working directory (CWD).
6	> All source scanning, reading, and vault output MUST stay within CWD and its subdirectories.
7	> If the user provides an external path, ask them to copy the files into CWD first.
8
9	## Mode Detection
10
11	On invocation, detect mode automatically:
12
13	1. Check for project markers in CWD:
14	- `package.json`, `pom.xml`, `build.gradle`, `Cargo.toml`, `go.mod`, `Makefile`,
15	`*.sln`, `pyproject.toml`, `setup.py`, `Gemfile`
16	2. If any marker found → Codebase Mode
17	3. If no marker found → Document Mode
18	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.
19	5. Announce detected mode and ask user to confirm or override.
20
21	---
22
23	## Document Mode
24
25	> Transforms knowledge sources (PDF, text, web, epub) into study notes.
26	> Templates: [templates.md](references/templates.md)
27
28	### Phase D1: Source Discovery & Extraction
29
30	1. Auto-scan CWD for `*/.pdf`, `*/.txt`, `*/.md`, `*/.html`, `*/.epub` (exclude `node_modules/`, `.git/`, `dist/`, `build/`, `StudyVault/`). Present for user confirmation.
31	2. Extract text (MANDATORY tools):
32	- 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.
33	```bash
34	pdftotext "source.pdf" "/tmp/source.txt"
35	```
36	- If `pdftotext` is not installed, install it first: `brew install poppler` (macOS) or `apt-get install poppler-utils` (Linux).
37	- URL → WebFetch
38	- Other formats (`.md`, `.txt`, `.html`) → Read directly.
39	3. Read extracted `.txt` files — understand scope, structure, depth. Work exclusively from the converted text, never from the raw PDF.
40	4. Source Content Mapping (MANDATORY for multi-file sources):
41	- Read cover page + TOC + 3+ sample pages from middle/end for EVERY source file
42	- NEVER assume content from filename — file numbering often ≠ chapter numbering
43	- Build verified mapping: `{ source_file → actual_topics → page_ranges }`
44	- Flag non-academic files and missing sources
45	- Present mapping to user for verification before proceeding
46
47	### Phase D2: Content Analysis
48
49	1. Identify topic hierarchy — sections, chapters, domain divisions.
50	2. Separate concept content vs practice questions.
51	3. Map dependencies between topics.
52	4. Identify key patterns — comparisons, decision trees, formulas.
53	5. Full topic checklist (MANDATORY) — every topic/subtopic listed. Drives all subsequent phases.
54
55	> Equal Depth Rule: Even a briefly mentioned subtopic MUST get a full dedicated note supplemented with textbook-level knowledge.
56
57	6. 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".
58	7. 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".
59
60	### Phase D3: Tag Standard
61
62	Define tag vocabulary before creating notes:
63	- Format: English, lowercase, kebab-case (e.g., `#data-hazard`)
64	- Hierarchy: top-level → domain → detail → technique → note-type
65	- Registry: Only registered tags allowed. Detail tags co-attach parent domain tag.
66
67	### Phase D4: Vault Structure
68
69	Create `StudyVault/` with numbered folders per [templates.md](references/templates.md). Group 3-5 related concepts per file.
70
71	### Phase D5: Dashboard Creation
72
73	Create `00-Dashboard/`: MOC, Quick Reference, Exam Traps. See [templates.md](references/templates.md).
74
75	- MOC: Topic Map + Practice Notes + Study Tools + Tag Index (with rules) + Weak Areas (with links) + Non-core Topic Policy
76	- Quick Reference: every heading includes `→ [[Concept Note]]` link; all key formulas
77	- Exam Traps: per-topic trap points in fold callouts, linked to concept notes
78
79	### Phase D6: Concept Notes
80
81	Per [templates.md](references/templates.md). Key rules:
82	- YAML frontmatter: `source_pdf`, `part`, `keywords` (MANDATORY)
83	- source_pdf MUST match verified Phase D1 mapping — never guess from filename
84	- If unavailable: `source_pdf: 원문 미보유`
85	- `[[wiki-links]]`, callouts (`[!tip]`, `[!important]`, `[!warning]`), comparison tables > prose
86	- ASCII diagrams for processes/flows/sequences
87	- Simplification-with-exceptions: general

People who liked this also viewed

6 picks

Type

tutor-setup

98installs89forks

View on GitHub

How to install tutor-setup?

bevibing/tutor-skills/tutor-setup

$npx -y skills add bevibing/tutor-skills --skill tutor-setup

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Tutor Setup — Knowledge to Obsidian StudyVault
2
3	## CWD Boundary Rule (ALL MODES)
4
5	> NEVER access files outside the current working directory (CWD).
6	> All source scanning, reading, and vault output MUST stay within CWD and its subdirectories.
7	> If the user provides an external path, ask them to copy the files into CWD first.
8
9	## Mode Detection
10
11	On invocation, detect mode automatically:
12
13	1. Check for project markers in CWD:
14	- `package.json`, `pom.xml`, `build.gradle`, `Cargo.toml`, `go.mod`, `Makefile`,
15	`*.sln`, `pyproject.toml`, `setup.py`, `Gemfile`
16	2. If any marker found → Codebase Mode
17	3. If no marker found → Document Mode
18	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.
19	5. Announce detected mode and ask user to confirm or override.
20
21	---
22
23	## Document Mode
24
25	> Transforms knowledge sources (PDF, text, web, epub) into study notes.
26	> Templates: [templates.md](references/templates.md)
27
28	### Phase D1: Source Discovery & Extraction
29
30	1. Auto-scan CWD for `*/.pdf`, `*/.txt`, `*/.md`, `*/.html`, `*/.epub` (exclude `node_modules/`, `.git/`, `dist/`, `build/`, `StudyVault/`). Present for user confirmation.
31	2. Extract text (MANDATORY tools):
32	- 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.
33	```bash
34	pdftotext "source.pdf" "/tmp/source.txt"
35	```
36	- If `pdftotext` is not installed, install it first: `brew install poppler` (macOS) or `apt-get install poppler-utils` (Linux).
37	- URL → WebFetch
38	- Other formats (`.md`, `.txt`, `.html`) → Read directly.
39	3. Read extracted `.txt` files — understand scope, structure, depth. Work exclusively from the converted text, never from the raw PDF.
40	4. Source Content Mapping (MANDATORY for multi-file sources):
41	- Read cover page + TOC + 3+ sample pages from middle/end for EVERY source file
42	- NEVER assume content from filename — file numbering often ≠ chapter numbering
43	- Build verified mapping: `{ source_file → actual_topics → page_ranges }`
44	- Flag non-academic files and missing sources
45	- Present mapping to user for verification before proceeding
46
47	### Phase D2: Content Analysis
48
49	1. Identify topic hierarchy — sections, chapters, domain divisions.
50	2. Separate concept content vs practice questions.
51	3. Map dependencies between topics.
52	4. Identify key patterns — comparisons, decision trees, formulas.
53	5. Full topic checklist (MANDATORY) — every topic/subtopic listed. Drives all subsequent phases.
54
55	> Equal Depth Rule: Even a briefly mentioned subtopic MUST get a full dedicated note supplemented with textbook-level knowledge.
56
57	6. 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".
58	7. 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".
59
60	### Phase D3: Tag Standard
61
62	Define tag vocabulary before creating notes:
63	- Format: English, lowercase, kebab-case (e.g., `#data-hazard`)
64	- Hierarchy: top-level → domain → detail → technique → note-type
65	- Registry: Only registered tags allowed. Detail tags co-attach parent domain tag.
66
67	### Phase D4: Vault Structure
68
69	Create `StudyVault/` with numbered folders per [templates.md](references/templates.md). Group 3-5 related concepts per file.
70
71	### Phase D5: Dashboard Creation
72
73	Create `00-Dashboard/`: MOC, Quick Reference, Exam Traps. See [templates.md](references/templates.md).
74
75	- MOC: Topic Map + Practice Notes + Study Tools + Tag Index (with rules) + Weak Areas (with links) + Non-core Topic Policy
76	- Quick Reference: every heading includes `→ [[Concept Note]]` link; all key formulas
77	- Exam Traps: per-topic trap points in fold callouts, linked to concept notes
78
79	### Phase D6: Concept Notes
80
81	Per [templates.md](references/templates.md). Key rules:
82	- YAML frontmatter: `source_pdf`, `part`, `keywords` (MANDATORY)
83	- source_pdf MUST match verified Phase D1 mapping — never guess from filename
84	- If unavailable: `source_pdf: 원문 미보유`
85	- `[[wiki-links]]`, callouts (`[!tip]`, `[!important]`, `[!warning]`), comparison tables > prose
86	- ASCII diagrams for processes/flows/sequences
87	- Simplification-with-exceptions: general

People who liked this also viewed

6 picks

Type