exam
Skill2 starsChanged 7 days agoMITView on GitHub
Run a realistic mock exam matching the real exam format, grade it, and produce a weak-spot report and revision plan. Use when the user wants a mock exam, practice exam, exam simulation or exam readiness check.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- LazyerIJ/self-clonetheir own version, first seen Oct 17, 2026
- devinat1/skillstheir own version, first seen Oct 6, 2026
- kubilaiswf/claude-tutortheir own version, first seen Sep 3, 2026
- dalvgit/vibechecktheir own version, first seen Jul 20, 2026
- dull-bird/teach-me-skilltheir own version, first seen Jul 8, 2026
- jiangtao/skillstheir own version, first seen Jan 29, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- dalvgit/vibecheck★ 4same name
- dull-bird/teach-me-skill★ 2same name
- LazyerIJ/self-clone★ 2same name
- devinat1/skills★ 1same name
- jiangtao/skills★ 1same name
- kubilaiswf/claude-tutor★ 0same 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.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- Example-Subject/CLAUDE.mdCLAUDE.md
- _template/CLAUDE.mdCLAUDE.md
- ingestSkill
- learnSkill
- quizSkill
- reviewSkill
- setupSkill
- statusSkill
- todaySkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read the subject's CLAUDE.md (exam format, date, emphasis), syllabus.md, progress.md, mistakes.md.
- Distinctive: line 10
If the format is unknown, ask once (or default: 20 MCQ + 3 open problems, 60 min).
- Distinctive: line 15
Use the search results for the coverage check too: a topic with only low scores (< ~0.6) is thin in the materials, so say so in the answer …
- Very specific: line 18
Run it: show all questions (or write an HTML version if html), state the time limit, start time (date), and say "answer when ready".
- Very specific: line 24
Update progress.md, mistakes.md and the session log, then run study log … --kind exam once per topic graded (Event log rule in …
“Common” is measured: kept by at least 6 in 10 of the 5 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
Mock exam
- Read the subject's
CLAUDE.md(exam format, date, emphasis),syllabus.md,progress.md,mistakes.md. If the format is unknown, ask once (or default: 20 MCQ + 3 open problems, 60 min). - Build the exam from my materials, cumulative across the syllabus, weighted by exam weight and emphasis,
with ~25 % targeted at weak topics and past mistakes. For each syllabus topic, find its sources with
~/Study/.tools/study search <Subject> "<topic>" -k 6(local model, ~2 s per call; batch the topics into one message rather than many calls), then Grepconverted/for exact formulas and names. Cite every answer. Use the search results for the coverage check too: a topic with only low scores (< ~0.6) is thin in the materials, so say so in the answer key rather than inventing material. Mix difficulty like a real exam. Keep an answer key with sources. Save it toexams/mock-exams/<date>.md(key in a section at the bottom). - Run it: show all questions (or write an HTML version if
html), state the time limit, start time (date), and say "answer when ready". No hints during the exam. - Grade: per-question marks, total and %, time used. For open problems give partial credit with a rubric.
- Report: readiness verdict (Not ready / Borderline / Ready), score by topic, top 3 weak spots with the misconception behind each, and a concrete revision plan until the exam date (which /learn and /review to run on which days). Save the report into the same file.
- Update
progress.md,mistakes.mdand the session log, then runstudy log … --kind examonce per topic graded (Event log rule in~/Study/CLAUDE.md).
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.