Exam Cram Coach · Flash

An AI exam-prep tutor for Claude Code, Codex, Cursor, Windsurf, Antigravity and Gemini CLI: drop in your lecture slides, notes, homework and past papers, and it teaches chapter by chapter with page citations, shows the figures, quizzes you with your own questions, tracks mistakes, and builds your cheat sheet.

English · 中文

# One-command install (Claude Code, Cursor, Codex, Antigravity, Windsurf, etc.)
npx skills add zekainie/universal-examprep-skill

One command to set up · Teaches from your files · Shows the figures · Quizzes from your homework · Never hides what it made up

Exam Cram Coach is an Agent Skill plus one small Python tool. You give a coding agent (Claude Code, Codex, Cursor, Windsurf, Antigravity, Gemini CLI, …) the folder with your lecture slides, notes, homework and past papers. It is engineered with three core technical differentiators:

1. 🎯 100% Grounded & Anti-Hallucination: Every taught concept cites exact file p.N references; out-of-scope queries exit with non-zero status to strictly prevent fabrication (100% out-of-scope abstention); transparent 🟢/🟡/⚠️ provenance tags distinguish materials from AI commentary.
2. 🧠 Cross-Session Persistent Memory: Maintains state locally in study_state.json and a mistake log without external vector databases or token bloat. Close your chat and resume anytime with coach.py status; mistakes are prioritized in spaced re-quizzing.
3. ⚡ High-End Performance on Cheap / Weak Models: Deterministic CLI output with 📍 next command hints and automated vector-figure cropping (pypdfium2). Benchmarked on 1,000+ pages of real college probability notes: Gemini Flash-Lite and Claude Haiku achieve zero command fabrication, zero phantom citations, and publication-grade figure presentations (see Weak Model Benchmark).

Core workflow:

• reads PDF / PPTX / DOCX / Markdown / TXT / HTML and splits the course into chapters;
• cuts the figures out of the lecture notes and the printed questions and solutions, so it can put the right picture in front of you while it explains;
• pulls the real questions and reference answers out of homework and exams (matches hw2.pdf with hw2solutions.pdf, and “Problem 1.3.10” with its solution);
• teaches chapter by chapter in plain words, quizzes only with those questions, tracks mistakes, and compiles a concise cheat sheet;
• labels every sentence so you always know where it came from:

Two editions, pick one

The rest of this page is about Flash: setup takes seconds even for a whole course, the whole skill is about 1,100 words, the study loop is seven commands, and it works with small models (tested with Gemini flash-lite and Claude Haiku). A feature-by-feature comparison is in Flash vs. the full edition.

Contents

1. Start studying in five minutes
2. What a study session looks like
3. Preparing your materials
4. Flash vs. the full edition
5. What ends up in the exam-cram/ folder
6. Command reference
7. Measured results
8. FAQ
9. For developers

Start studying in five minutes

Step 0 · What you need

• A coding agent with a terminal: Claude Code, Codex, Cursor, Windsurf, Antigravity, Gemini CLI, or any other agent that can run shell commands and read files. For PDF-heavy courses prefer the desktop app or IDE version of your agent: terminals often cannot display the figures.
• Python 3.8 or newer. Check with python --version. On Windows, install it from python.org and tick Add python.exe to PATH.
• Optional but recommended: pip install pypdfium2. It gives PDF text extraction and figure cropping. Without it, PDFs are listed as “needs pypdfium2” and everything else (PPTX, DOCX, Markdown, TXT) still works.

Step 1 · Install the skill

Easiest: let the agent do it. Copy this to your agent; it may ask you to approve network access or writing to its skills folder:

Install the Exam Cram Coach skill: download exam-cram-coach-flash.zip from the latest release at https://github.com/ZeKaiNie/universal-examprep-skill/releases/latest (or git clone the repository) and put it in your user-level skills directory so that SKILL.md and coach.py end up in a folder named exam-cram-coach. Back up any older copy first. Then run `pip install pypdfium2` and `python <that folder>/coach.py doctor`, and report the install path and the doctor output.

Per-host versions:

Install or update https://github.com/ZeKaiNie/universal-examprep-skill into ~/.claude/skills/exam-cram-coach (SKILL.md and coach.py must be directly inside that folder). Ask before overwriting an existing copy. Then run `pip install pypdfium2` and `python ~/.claude/skills/exam-cram-coach/coach.py doctor` and show me the result.

Install the latest Exam Cram Coach skill from https://github.com/ZeKaiNie/universal-examprep-skill into my Codex skills directory as exam-cram-coach (SKILL.md and coach.py directly inside). Back up any older copy. Run `pip install pypdfium2`, then `python <install path>/coach.py doctor`, report the path and the output, and tell me whether I need a new task for the skill to appear.

Fetch https://github.com/ZeKaiNie/universal-examprep-skill and install it as exam-cram-coach in my Cursor user skills directory (~/.cursor/skills/ or ~/.agents/skills/), SKILL.md and coach.py directly inside. Back up an older copy, run `pip install pypdfium2`, confirm Cursor discovers SKILL.md, and report the path.

Fetch https://github.com/ZeKaiNie/universal-examprep-skill and install it in ~/.codeium/windsurf/skills/exam-cram-coach. Ask before downloading or replacing files. Run `pip install pypdfium2`, confirm Cascade discovers SKILL.md, and report the path.

Fetch https://github.com/ZeKaiNie/universal-examprep-skill and install it in ~/.gemini/antigravity/skills/exam-cram-coach (SKILL.md and coach.py directly inside). Ask before writing outside the workspace. Run `pip install pypdfium2`, rescan skills, and report the path and `python <path>/coach.py doctor`.

gemini skills install https://github.com/ZeKaiNie/universal-examprep-skill.git
pip install pypdfium2

Manual install. Download exam-cram-coach-flash.zip and unzip it into your agent's skills folder. You should end up with …/skills/exam-cram-coach/SKILL.md and …/skills/exam-cram-coach/coach.py. Then open a terminal and run pip install pypdfium2.

To check the install from any terminal:

python path/to/exam-cram-coach/coach.py doctor

It prints the version, whether PDF support is available, and the last workspace used.

Step 2 · Put your materials in one folder

Anything goes in one folder (sub-folders are fine): slides, lecture notes, textbook chapters, homework, solutions, quizzes, past exams. See Preparing your materials for naming tips that make chapters and answers line up automatically. Your own scanned homework can stay in the folder: it is detected and never shown as an answer.

Step 3 · Send the first message

Use the Exam Cram Coach skill. My materials are in D:\Courses\Probability. The exam is in 3 days, I am starting from zero, teach me in English from chapter 1.

The agent will run one command (coach.py setup), which takes a few seconds even for a thousand pages, and reply with the chapter list, the number of questions it found, and any warning such as “3 PDFs need pip install pypdfium2” or “file X has no text, I will open it directly”. Then it starts teaching chapter 1.

Step 4 · Keep talking normally

Every reply ends with a 📍 progress line (chapter and part, quiz score, mistakes, days left, next step) copied from the tool, so a long session never loses its place.

What a study session looks like

This is what a student saw in a real session on a probability course (Gemini flash-lite, translated from Chinese). Where the transcript shows ![](…png) the chat displayed a figure that setup had cut out of the lecture PDF:

Chapter 1: Set Theory

🟢 A set is a collection of things. Capital letters name sets (A), small letters name elements (x). x ∈ A means x is an element of A, x ∉ A means it is not. (ch01.pdf p.3)

🟢 Union A ∪ B: everything that is in A or in B or in both — on a Venn diagram, the whole area both circles cover. (ch01.pdf p.4)

[figure cropped from ch01.pdf p.4 shown here]

🟢 Partition: a family of sets that is both mutually exclusive and collectively exhaustive. (ch01.pdf p.9)

These are the foundation for everything that follows. Say “next” when you are ready for the examples.

Later, on a homework question whose statement is only a textbook number:

Quiz · Problem 1.1.2 (hw1.pdf p.1)

🟡 Givens, restated from the reference answer: a pizza is either Tuscan (T) or Neapolitan (N), so {N, T} is a partition; M = mushrooms, O = onions. Are N and M mutually exclusive? Are N and T collectively exhaustive? …

(student: “I can't do it, show me the answer”)

🟢 Reference solution (hw1solution.pdf p.1): since N = Tᶜ, N ∩ M ≠ ∅, so N and M are not mutually exclusive. N ∪ T = S, so they are collectively exhaustive. From the diagram T and O do not overlap …

[the solution's Venn diagram, cropped from hw1solution.pdf p.1, shown here]

Record it with python coach.py answer q001 right or … wrong, or say “next”.

Every fact carries a page; every picture is a crop of the original file; the answer figure appears only after you asked for the answer. The crops look like this (from the MIT 6.006 lecture notes and Quiz 1, CC BY-NC-SA, produced by setup with no manual work):

  

Preparing your materials

The tool works on any layout, but a few habits make the automatic chapter split and answer matching perfect:

Supported input: .pdf (needs pypdfium2 or pypdf), .pptx, .docx, .md, .txt, .html, and image files. Excel files and audio are not read.

Flash vs. the full edition

Use Flash unless you specifically want the printable HTML/PDF study guides of v4.3. Both editions stay in this repository (full/ is the v4.3 tree, unchanged, with its own README and tests). They do not share workspaces: after switching, re-run setup on the materials folder.

What ends up in the exam-cram/ folder

setup creates one folder next to your materials (or where --workspace points). Everything is plain text or PNG; nothing is uploaded anywhere.

Delete the folder to start over, or run setup … --fresh.

Command reference

You normally never type these; the agent does. They are useful for checking on things or for automation.

python coach.py setup <folder> [--days N] [--lang zh|en] [--name COURSE] [--start N] [--slice CHARS] [--fresh]
python coach.py status                        progress panel
python coach.py next [--repeat|--back]        next slice of the current chapter + its figures
python coach.py chapter N [--part K]          inspect chapter N (list parts or print one)
python coach.py goto N [--restart]            switch chapter
python coach.py ask "keywords" [-k 5] [--chapter N]      search the materials (exit code 4 = nothing found)
python coach.py quiz [-n 3] [--chapter N] [--all]        pick questions (open mistakes first)
python coach.py check <id>                    reference answer, its source and answer figure
python coach.py answer <id> right|wrong|skip [--note …]  record a result
python coach.py done [--chapter N]            finish the chapter, move on
python coach.py note "…" [--type summary|confusion|note] [--chapter N]
python coach.py mistakes [--answers]          open mistakes
python coach.py cheatsheet [--out FILE]       build the cheat sheet
python coach.py plan [--days N]               day-by-day plan for the remaining chapters (--days updates the exam date)
python coach.py export [--to DIR] [--qid …] [--chapter N] [paths…]   copy figures where the chat UI can render them
python coach.py figures [--chapter N] [--file F] [--page P]   list cropped figures
python coach.py figure <file> <page> [--crop x0,y0,x1,y1] [--scale 2]   render a page or a region
python coach.py doctor                        environment check
python coach.py help

--workspace PATH (or the environment variable EXAM_CRAM_WORKSPACE) selects a workspace; otherwise the last one used is remembered. --slice 2000 makes each teaching slice shorter for small models.

Measured results

All numbers were measured on a Windows 11 laptop with Python 3.12; the commands are in docs/v5-refactor.md.

Setup speed and extraction quality

Weak models actually follow it. Four-turn Chinese session on EEC 160 with only SKILL.md as guidance (docs/weak-model-test.md):

Compared with v4.3 on the same MIT course: skill text read by the agent 140 KB → 6.5 KB; script calls before the first explanation 5 → 1; unit-test suite 12 minutes → under one second; repository 144k lines → 2.5k.

FAQ

The agent says PDFs need pypdfium2. Run pip install pypdfium2 (on Windows, py -m pip install pypdfium2 if pip is not found), then ask the agent to run setup again. pypdf also works for text but cannot crop figures.

python is not recognized. Install Python from python.org and tick Add python.exe to PATH, or tell the agent the full path to your Python.

I don't see the pictures in the chat. Two different causes. Terminals cannot render images at all: use the desktop or IDE version of your agent, or open the PNG path it printed. Chat panels built on VS Code / Electron (Cursor, Windsurf, Antigravity, VS Code extensions) do render images, but block file:// paths outside the opened workspace or in a Temp folder: the skill then runs coach.py export --to <a folder inside the workspace or the host's artifact folder> and embeds the copied files. If a picture still does not appear, the agent has at least opened it and can describe it, and gives you the path to click.

My slides are scans without text. They are listed as “no text”; the agent can render any page with coach.py figure <file> <page> and read it with its own vision. Handwritten homework is skipped on purpose.

A question shows only “Problem 1.4.4”. The statement is in the textbook, not in your folder. The quiz prints the givens from the start of the reference solution (🟡) and the agent teaches from the solution; it must not invent a different problem.

No questions were found. Check the naming tips above; questions need a number or label at the start of a line. quiz --all draws from every chapter.

Chapters are wrong. Put the chapter number in the file name (lec3, 第3章, 03-…), or split a combined file. coach.py chapter N shows what each chapter contains.

Several courses. Each materials folder gets its own exam-cram/; the last one used is remembered, or pass --workspace.

Start over / change the exam date. setup <folder> --fresh discards progress; setup <folder> --days 2 updates the date and keeps progress.

Where does my data go? Nowhere. The tool only writes into exam-cram/. Your agent host sees the text and images it prints, the same as any file you open with the agent.

Can I use it without an agent? Yes: every command prints plain text, so python coach.py next and python coach.py quiz work as a reading and drill tool on their own.

Can I use it in a web chat without Python? The skill has a fallback (§7 of SKILL.md), but progress, figures and quizzes work much better with a local agent.

For developers

git clone https://github.com/ZeKaiNie/universal-examprep-skill exam-cram-coach
cd exam-cram-coach
pip install pypdfium2
python -m unittest discover -s tests -v          # 43 tests, about a second
python coach.py setup samples/zh-data-structures  # bundled Chinese sample course
python samples/fetch.py                           # MIT 6.006 + Yale PSYC 110 (CC BY-NC-SA)
python eval/agent_smoke.py claude --model claude-haiku-4-5-20251001 --materials <folder>   # drive a real agent
python release.py                                 # build dist/exam-cram-coach-flash.zip

Layout: SKILL.md (what the agent follows), coach.py + coach/ (extract → chapters → questions → figures → index → state → cli), tests/, samples/, eval/ (agent smoke test and scorer), docs/ (refactor report, feature audit, weak-model test). Release history is in CHANGELOG.md; contribution notes in CONTRIBUTING.md.

Keywords

So that people and agents searching in either language find this page: exam prep · final exam cram · midterm revision · study from lecture slides PDF / PPTX · AI tutor that cites sources · quiz from homework and past papers · mistake notebook · cheat sheet generator · study plan for N days · figures extracted from lecture notes · Agent Skill for Claude Code / Codex / Cursor / Windsurf / Antigravity / Gemini CLI · works with small local models · offline, no server, Python, MIT. 期末复习 · 考前突击 · 期中复习 · 考研/考证复习 · 课件 PDF 讲解 · AI 家教 · 引用出处不编造 · 用作业和真题刷题 · 错题本 · 考前小抄 · 复习计划 · 讲义配图 · Claude Code / Codex / Cursor 智能体技能 · 本地运行 · 开源。

License

MIT. Sample courses keep their own licenses (see samples/README.md); the two example crops above come from MIT OpenCourseWare 6.006 (CC BY-NC-SA 4.0). Good luck with your exam. 🎓