quiz
Skill2 starsChanged 7 days agoMITView on GitHub
Generate a multiple-choice or practice quiz from the course materials, in chat or as a self-grading HTML file, and record results. Use when the user asks for a quiz, test, MCQ, practice questions or problems.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- TakaGoto/rag-learning-academytheir own version, first seen Oct 28, 2026
- ajitta/know-your-unknownstheir own version, first seen Oct 27, 2026
- ProjectAJ14/eklavyatheir own version, first seen Oct 20, 2026
- simoncorry/foundrytheir own version, first seen Oct 7, 2026
- TimCodes04/second-braintheir own version, first seen Sep 23, 2026
- qiao/quiztheir own version, first seen Sep 17, 2026
Used with
Projects with it also use progress.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
remenoscodesSkillprogress
Longitudinal language learning progress report with metrics, trends, and insights
Also in 4 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- maludb/learn-claude★ 51same name
- simoncorry/foundry★ 39same name
- alexiocassanifm/anthropic-certifications★ 36same name
- ProjectAJ14/eklavya★ 29same name
- TakaGoto/rag-learning-academy★ 24same name
- joyehuang/skills★ 9same name
- Aetheria-Labs1/storefront-skills★ 8same name
- ajitta/know-your-unknowns★ 2same name
- qiao/quiz★ 2same name
- andrewn6/claude-code-101★ 1same name
4 more not listed
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.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- Example-Subject/CLAUDE.mdCLAUDE.md
- _template/CLAUDE.mdCLAUDE.md
- examSkill
- ingestSkill
- learnSkill
- reviewSkill
- setupSkill
- statusSkill
- todaySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
1
Distinctive
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 10
Read CLAUDE.md for the exam's question style and mirror it.
- Very specific: line 17
HTML mode (
html): write exams/quizzes/<date>-<topic>.html — a single self-contained file (no external resources) with the questions, … - Very specific: line 21
Update memory: each question counts as a recall for its topic (reschedule per the ladder in ~/Study/CLAUDE.md), log misses in mistakes.md, …
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Quiz (default 10 questions, in chat)
- Resolve subject and scope: a topic,
weak(Level ≤ 2 + unfixed mistakes), orall(weighted by exam weight). ReadCLAUDE.mdfor the exam's question style and mirror it. - Build questions only from my materials: find sources with
~/Study/.tools/study search <Subject> "<topic>" -k 6and Grepconverted/for exact terms, then read the sources. Mix: ~70 % MCQ (4 options, one correct, distractors from real misconceptions andmistakes.md, no "all of the above"), ~30 % short practice problems / short answer. Each question stores its source citation. - Chat mode (default): show questions in blocks of 5; I answer compactly like
1b 2d 3a …or text. Then grade all, show score, and for each miss: correct answer, why my option is tempting but wrong, source. - HTML mode (
html): writeexams/quizzes/<date>-<topic>.html— a single self-contained file (no external resources) with the questions, instant feedback per question, explanations + sources, a score, and a "Copy results" button producing text likeQUIZ RESULTS <topic>: 1✅ 2❌(chose b) …. Open it withopen <file>. When I paste the results back, grade-log them as below. - Update memory: each question counts as a recall for its topic (reschedule per the ladder in
~/Study/CLAUDE.md), log misses inmistakes.md, append a line to the session log, then runstudy log … --kind quizonce per topic (Event log rule).
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.