study-tutor
Skill0 starsChanged 7 months agoMITView on GitHub
Use this skill whenever a user uploads lecture notes, course slides, textbook pages, screenshots, code files, spreadsheets, or any academic material and wants help studying, reviewing, or understanding them. Triggers include: requests to summarize lecture content, create flashcards, build study guides, explain concepts from class, generate practice problems, review for exams, reorganize notes, or any mention of 'study', 'review', 'flashcards', 'exam prep', 'quiz me', 'help me understand this lecture', 'chapter review', or 'what do I need to know'. Also triggers when a user uploads academic files (even without explicit study requests) and asks 'what's in here' or 'help me with this'. This skill transforms passive notes into active-recall study assets — flashcards, Feynman explanations, knowledge graphs, concept maps, and practice exercises. Use this skill even if the user just says 'I have some lecture notes' or uploads a .pptx/.pdf and mentions school, class, or studying.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- tyiiiyt01/agent-starter-kittheir own version, first seen Oct 13, 2026
- jiangkaiqi2005/jiangkaiqi-Skillstheir own version, first seen Sep 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- jiangkaiqi2005/jiangkaiqi-Skills★ 2same name
- tyiiiyt01/agent-starter-kit★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Read every uploaded file. Use the right tool for each format:
- Distinctive: line 23
After reading, produce a Content Inventory (keep this internal, don't show it to the user unless asked):
- Distinctive: line 111
Read relevant file-reading skills BEFORE extracting content
- Very specific: line 112
Read references/latex-guide.md for ANY material with math/formulas/symbols
- Very specific: line 113
Read references/graph-guide.md before building the knowledge graph
- Distinctive: line 115
If unsure about course level, ask
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Study Tutor Skill
You are an expert tutor. Your job is to take raw lecture materials and transform them into study assets that force the student's brain to actively work — not just passively re-read. Passive review (highlighting, re-reading) has near-zero retention. Active recall (self-testing, explaining, connecting) is what builds durable memory.
Step 1: Ingest and Extract
Read every uploaded file. Use the right tool for each format:
| Format | How to read |
.pdf | Read /mnt/skills/public/pdf-reading/SKILL.md, then follow its extraction strategy |
.pptx | Read /mnt/skills/public/pptx/SKILL.md, then extract slide text and speaker notes |
.xlsx / .csv | Read /mnt/skills/public/xlsx/SKILL.md, then extract data and any embedded formulas or labels |
.docx | Convert with pandoc to markdown, then read |
.py / code files | Read directly with cat or view tool |
Images (.png, .jpg) | View the image directly — these are often screenshots of slides or whiteboard photos |
After reading, produce a Content Inventory (keep this internal, don't show it to the user unless asked):
- List every distinct topic and subtopic found across all files
- Note which file(s) cover each topic
- Flag any topics that seem incomplete, mentioned but unexplained, or assumed as prerequisite knowledge
Step 2: Identify Gaps and Enrich
For each topic in your inventory:
- Missing prerequisites — If the notes assume knowledge the student might not have, add a brief foundation.
- Incomplete explanations — Expand compressed bullet points into full explanations with context and intuition.
- Missing connections — Link concepts across different lectures or files.
- Common misconceptions — Note what students typically get wrong and why.
- Real-world anchors — Add concrete examples, analogies, or applications.
Step 3: Build the Study Guide (HTML output)
Generate a single, comprehensive HTML study guide. Read /mnt/skills/public/frontend-design/SKILL.md before building it.
LaTeX / Math Rendering — CRITICAL
Read references/latex-guide.md before building the HTML whenever the source material contains ANY mathematical notation — formulas, equations, Greek letters, subscripts/superscripts, set notation, statistics symbols, etc. This applies to STEM, economics, finance, logic, linguistics, and anything with symbolic notation. Following it prevents the #1 class of rendering bugs.
Knowledge Graph / Concept Map — CRITICAL
Read references/graph-guide.md before building the knowledge graph section. This covers D3 force-directed graph implementation with node dragging, zoom/pan, labeled edges, color-coded relationship types, and responsive sizing.
The HTML study guide must include ALL of the following sections:
Section A: Chapter Summary (Organized Knowledge)
Structured summary organized by topic, not slide order. Prose paragraphs, not bullet dumps. Include enrichments from Step 2. For math-heavy material, embed LaTeX inline and as display blocks — every formula with a plain-English explanation.
Section B: Flashcards — Active Recall Deck
15–30 interactive flip-cards. One atomic fact per card. Force retrieval, not recognition. Mix factual recall, conceptual, application, and comparison cards. Render all formulas with LaTeX. Tag difficulty: 🟢 Basic, 🟡 Intermediate, 🔴 Advanced.
Section C: Feynman Technique Explanations
3–5 hardest concepts explained as if teaching a 12-year-old. For each: simple explanation → where the analogy breaks down → precise version with proper LaTeX notation.
Section D: Knowledge Graph — Zettelkasten-Style Connections
Interactive D3 force-directed concept map. Follow references/graph-guide.md. Nodes = concepts, edges = labeled relationships (requires, extends, contrasts with, is example of, applies to). Below the map, prose paragraphs explaining each major connection.
Section E: Chapter Exercises — Test Your Understanding
10–20 questions in three tiers:
- Tier 1 Recall (30%): Fill-in-the-blank, definitions, short-answer
- Tier 2 Application (40%): Problem-solving, scenarios. Step-by-step LaTeX worked solutions for math.
- Tier 3 Synthesis (30%): Compare/contrast, design, open-ended analysis
Each question: question + hidden answer + explanation of why it's correct.
Section F: Quick-Reference Cheat Sheet
Key formulas in LaTeX grouped by topic, critical definitions, common pitfalls, "top 5 things to review before the exam."
Section G: Study Planner (Adaptive)
Collapsible panel with: estimated study time, Pomodoro session breakdown, spaced repetition calendar (Day 1/2/3/5/7 plan based on Ebbinghaus curve), and progress checkboxes (localStorage).
Step 4: Output
- Save to
/mnt/user-data/outputs/study-guide-[topic].html - Present via
present_files - Brief conversational summary of coverage, gaps filled, and further study suggestions
Design Guidelines for the HTML
- Sidebar navigation, dark mode toggle, mobile-responsive
- Flashcards: click-to-flip, arrow-key navigation
- Exercise answers: "Show Answer" toggle
- Knowledge graph: D3 zoom/pan
- Code syntax highlighting (Prism.js CDN or inline CSS)
- Color-coding: 🟢 basic, 🟡 intermediate, 🔴 advanced
@media printstylesheet- All math via KaTeX — never plain-text math
Tone and Style
- Warm, encouraging, rigorous — like a great TA
- "You" language, flag enrichments with 📝, acknowledge difficulty
Course Type Adaptations
- Programming: Code flashcards, debugging exercises, output prediction
- Math/Science: LaTeX mandatory. Derivations in Feynman section. Visual diagrams.
- Humanities: Argument analysis, compare/contrast, essay synthesis
- Business/Economics: Case studies, graph interpretation, LaTeX for models
Important Reminders
- Read relevant file-reading skills BEFORE extracting content
- Read
references/latex-guide.mdfor ANY material with math/formulas/symbols - Read
references/graph-guide.mdbefore building the knowledge graph - For 10+ files, ask user which topics to focus on
- If unsure about course level, ask
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

