tutor

Name: tutor
Author: bevibing

104installs89forks

How to install tutor?

bevibing/tutor-skills/tutor

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

Installs into the current project.

Summary

Interactive quiz tutor for Obsidian StudyVault learning. Use when the user wants to: (1) Take a diagnostic assessment of their knowledge, (2) Study or review specific sections/topics, (3) Drill weak areas identified in previous sessions, (4) Check their learning progress or dashb

Files · 1

View on GitHub

SKILL.md

1	# Tutor Skill
2
3	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.
4
5	## File Structure
6
7	```
8	StudyVault/
9	├── dashboard ← Compact overview: proficiency table + stats
10	└── concepts/
11	├── {area-name}.md ← Per-area concept tracking (attempts, status, error notes)
12	└── ...
13	```
14
15	- Dashboard: Only aggregated numbers. Links to concept files. Stays small forever.
16	- Concept files: One per area. Tracks each concept with attempts, correct count, date, status, and error notes. Grows proportionally to unique concepts tested (bounded).
17
18	## Workflow
19
20	### Phase 0: Detect Language
21
22	Detect user's language from their message → `{LANG}`. All output and file content in `{LANG}`.
23
24	### Phase 1: Discover Vault
25
26	1. Glob `**/StudyVault/` in project
27	2. List section directories
28	3. Glob `*/StudyVault/dashboard*` to find dashboard
29	4. If found, read it. Preserve existing file path regardless of language.
30	5. If not found, create from template (see Dashboard Template below)
31
32	If no StudyVault exists, inform user and stop.
33
34	### Phase 2: Ask Session Type
35
36	MANDATORY: Use AskUserQuestion to let the user choose what to do. Analyze the dashboard to build context-aware options, then present them.
37
38	Read the dashboard proficiency table and build options based on current state:
39
40	1. If unmeasured areas (⬜) exist → include "Diagnostic" option targeting those areas
41	2. If weak areas (🟥/🟨) exist → include "Drill weak areas" option naming the weakest area(s)
42	3. Always include "Choose a section" option so the user can pick any area
43	4. If all areas are 🟩/🟦 → include "Hard-mode review" option
44
45	Present these as an AskUserQuestion with header "Session" and concise descriptions showing which areas each option targets. The user MUST select before proceeding.
46
47	### Phase 3: Build Questions
48
49	1. Read markdown files in target section(s)
50	2. If drilling weak area: also read `concepts/{area}.md` to find 🔴 unresolved concepts — rephrase these in new contexts (don't repeat the same question)
51	3. Craft exactly 4 questions following `references/quiz-rules.md`
52
53	CRITICAL: Read `references/quiz-rules.md` before crafting ANY question. Zero hints allowed.
54
55	### Phase 4: Present Quiz
56
57	Use AskUserQuestion:
58	- 4 questions, 4 options each, single-select
59	- Header: "Q1. Topic" (max 12 chars)
60	- Descriptions: neutral, no hints
61
62	### Phase 5: Grade & Explain
63
64	1. Show results table (question / correct answer / user answer / result)
65	2. Wrong answers: concise explanation
66	3. Map each question to its area
67
68	### Phase 6: Update Files
69
70	#### 1. Update concept file (`concepts/{area}.md`)
71
72	For each question answered:
73	- New concept: Add row to table + if wrong, add error note under `### 오답 메모` (or localized equivalent)
74	- Existing 🔴 concept answered correctly: Increment attempts & correct, change status to 🟢, keep error note (learning history)
75	- Existing 🟢 concept answered wrong again: Increment attempts, change status back to 🔴, update error note
76
77	Table format:
78	```markdown
79	\| Concept \| Attempts \| Correct \| Last Tested \| Status \|
80	\|---------\|----------\|---------\|-------------\|--------\|
81	\| concept name \| 2 \| 1 \| 2026-02-24 \| 🔴 \|
82	```
83
84	Error notes format (only for wrong answers):
85	```markdown
86	### Error Notes
87
88	concept name
89	- Confusion: what the user mixed up
90	- Key point: the correct understanding
91	```
92
93	#### 2. Update dashboard
94
95	- Recalculate per-area stats from concept files (sum attempts/correct across all concepts in that area)
96	- Update proficiency badges: 🟥 0-39% · 🟨 40-69% · 🟩 70-89% · 🟦 90-100% · ⬜ no data
97	- Update stats: total questions, cumulative rate, unresolved/resolved counts, weakest/strongest
98
99	Dashboard stays compact — no session logs, no per-question details.
100
101	## Dashboard Template
102
103	Create when no dashboard exists. Filename localized to `{LANG}`. Example in English:
104
105	```markdown
106	# Learning Dashboard
107
108	> Concept-based metacognition tracking. See linked files for details.
109
110	---
111
112	## Proficiency by Area
113
114	\| Area \| Correct \| Wrong \| Rate \| Level \| Details \|
115	\|------\|---------\|-------\|------\|-------\|---------\|
116	(one row per section, last column = [[concepts/{area}]] link)
117	\| Total \| 0 \| 0 \| - \| ⬜ Unmeasured \| \|
118
119	> 🟥 Weak (0-39%) · 🟨 Fair (40-69%) · 🟩 Good (70-89%) · 🟦 Mastered (90-100%) · ⬜ Unmeasured
120
121	---
122
123	## Stats
124
125	- Total Questions: 0
126	- Cumulative Rate: -
127	- Unresolved Concepts: 0
128	- Resolved Concepts: 0
129	- Weakest Area: -
130	- Strongest Area: -
131	```
132
133	## Concept File Template
134
135	Creat

People who liked this also viewed

6 picks

Type

tutor

104installs89forks

View on GitHub

How to install tutor?

bevibing/tutor-skills/tutor

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Tutor Skill
2
3	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.
4
5	## File Structure
6
7	```
8	StudyVault/
9	├── dashboard ← Compact overview: proficiency table + stats
10	└── concepts/
11	├── {area-name}.md ← Per-area concept tracking (attempts, status, error notes)
12	└── ...
13	```
14
15	- Dashboard: Only aggregated numbers. Links to concept files. Stays small forever.
16	- Concept files: One per area. Tracks each concept with attempts, correct count, date, status, and error notes. Grows proportionally to unique concepts tested (bounded).
17
18	## Workflow
19
20	### Phase 0: Detect Language
21
22	Detect user's language from their message → `{LANG}`. All output and file content in `{LANG}`.
23
24	### Phase 1: Discover Vault
25
26	1. Glob `**/StudyVault/` in project
27	2. List section directories
28	3. Glob `*/StudyVault/dashboard*` to find dashboard
29	4. If found, read it. Preserve existing file path regardless of language.
30	5. If not found, create from template (see Dashboard Template below)
31
32	If no StudyVault exists, inform user and stop.
33
34	### Phase 2: Ask Session Type
35
36	MANDATORY: Use AskUserQuestion to let the user choose what to do. Analyze the dashboard to build context-aware options, then present them.
37
38	Read the dashboard proficiency table and build options based on current state:
39
40	1. If unmeasured areas (⬜) exist → include "Diagnostic" option targeting those areas
41	2. If weak areas (🟥/🟨) exist → include "Drill weak areas" option naming the weakest area(s)
42	3. Always include "Choose a section" option so the user can pick any area
43	4. If all areas are 🟩/🟦 → include "Hard-mode review" option
44
45	Present these as an AskUserQuestion with header "Session" and concise descriptions showing which areas each option targets. The user MUST select before proceeding.
46
47	### Phase 3: Build Questions
48
49	1. Read markdown files in target section(s)
50	2. If drilling weak area: also read `concepts/{area}.md` to find 🔴 unresolved concepts — rephrase these in new contexts (don't repeat the same question)
51	3. Craft exactly 4 questions following `references/quiz-rules.md`
52
53	CRITICAL: Read `references/quiz-rules.md` before crafting ANY question. Zero hints allowed.
54
55	### Phase 4: Present Quiz
56
57	Use AskUserQuestion:
58	- 4 questions, 4 options each, single-select
59	- Header: "Q1. Topic" (max 12 chars)
60	- Descriptions: neutral, no hints
61
62	### Phase 5: Grade & Explain
63
64	1. Show results table (question / correct answer / user answer / result)
65	2. Wrong answers: concise explanation
66	3. Map each question to its area
67
68	### Phase 6: Update Files
69
70	#### 1. Update concept file (`concepts/{area}.md`)
71
72	For each question answered:
73	- New concept: Add row to table + if wrong, add error note under `### 오답 메모` (or localized equivalent)
74	- Existing 🔴 concept answered correctly: Increment attempts & correct, change status to 🟢, keep error note (learning history)
75	- Existing 🟢 concept answered wrong again: Increment attempts, change status back to 🔴, update error note
76
77	Table format:
78	```markdown
79	\| Concept \| Attempts \| Correct \| Last Tested \| Status \|
80	\|---------\|----------\|---------\|-------------\|--------\|
81	\| concept name \| 2 \| 1 \| 2026-02-24 \| 🔴 \|
82	```
83
84	Error notes format (only for wrong answers):
85	```markdown
86	### Error Notes
87
88	concept name
89	- Confusion: what the user mixed up
90	- Key point: the correct understanding
91	```
92
93	#### 2. Update dashboard
94
95	- Recalculate per-area stats from concept files (sum attempts/correct across all concepts in that area)
96	- Update proficiency badges: 🟥 0-39% · 🟨 40-69% · 🟩 70-89% · 🟦 90-100% · ⬜ no data
97	- Update stats: total questions, cumulative rate, unresolved/resolved counts, weakest/strongest
98
99	Dashboard stays compact — no session logs, no per-question details.
100
101	## Dashboard Template
102
103	Create when no dashboard exists. Filename localized to `{LANG}`. Example in English:
104
105	```markdown
106	# Learning Dashboard
107
108	> Concept-based metacognition tracking. See linked files for details.
109
110	---
111
112	## Proficiency by Area
113
114	\| Area \| Correct \| Wrong \| Rate \| Level \| Details \|
115	\|------\|---------\|-------\|------\|-------\|---------\|
116	(one row per section, last column = [[concepts/{area}]] link)
117	\| Total \| 0 \| 0 \| - \| ⬜ Unmeasured \| \|
118
119	> 🟥 Weak (0-39%) · 🟨 Fair (40-69%) · 🟩 Good (70-89%) · 🟦 Mastered (90-100%) · ⬜ Unmeasured
120
121	---
122
123	## Stats
124
125	- Total Questions: 0
126	- Cumulative Rate: -
127	- Unresolved Concepts: 0
128	- Resolved Concepts: 0
129	- Weakest Area: -
130	- Strongest Area: -
131	```
132
133	## Concept File Template
134
135	Creat

People who liked this also viewed

6 picks

Type