agentleFS
leoleolroleoleolro/career-os/.claude/skills/study/SKILL.md

study

Skill0 starsChanged 55 days agoMITView on GitHub

Quiz the candidate for a certification exam from a question bank, grade, explain, and track weak topics. Use when the candidate says "study", "quiz me", "practice exam", "EDMCS", "Oracle exam", "Claude architect exam", "/study".

21 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Ask n (default 10) questions one at a time, exam wording, options A–E, never show the [x] marks.

    line 14
  2. Distinctive:

    After each answer: correct/incorrect, the right answer, a 2–4 line explanation of *why* (and why the distractors are wrong).

    line 15
  3. Distinctive:

    Don't pad with trivia; exam-style only.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 17 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/study [bank | topic] [n]

Banks

  • profile/study/<exam>-question-bank.txt — practice questions with [x]-marked answers.
  • EDMCS (Enterprise Data Management) — no bank yet. Ask the candidate to drop one in inbox/ (docx/pdf/txt → convert with textutil -convert txt or pypdf) and move it to profile/study/. Until then, generate questions from the official exam topics (WebSearch "Oracle Enterprise Data Management 2025 Implementation Professional exam topics" and cite the page) — label them as generated, not official.
  • Claude Certified Architect – Foundations — domains: Agentic Architecture 27%, Claude Code Workflows 20%, Prompt Engineering 20%, Tool Design & MCP 18%, Context Management 15%. Generate scenario questions at that weighting; ground answers in the Claude docs (WebFetch docs.claude.com) rather than memory when unsure.

Session

  1. Ask n (default 10) questions one at a time, exam wording, options A–E, never show the [x] marks. Multi-select questions say "choose N".
  2. After each answer: correct/incorrect, the right answer, a 2–4 line explanation of why (and why the distractors are wrong).
  3. End: score, list of missed topics, and append to data/study.json: {date, bank, asked, correct, weakTopics:[…]} (create the file if missing). Next session, start with the weak topics.
  4. Offer a 5-minute "teach-back": the candidate explains a weak topic in their own words; you correct gently.

Don't pad with trivia; exam-style only. If a bank question is malformed or its marked answer looks wrong, say so rather than teaching an error.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.