agentleFS
Sign inStart free
SirjanSinghSirjanSingh/oahelper-mcp/skills/mcq-drill/SKILL.md

mcq-drill

Skill2 starsChanged 27 days agoMITView on GitHub

Quiz the user one MCQ at a time from a company's real OA multiple-choice questions and answer keys saved by the oahelper MCP server, with scoring and explanations. Use when the user says "quiz me", "MCQ practice for X", "drill aptitude", "test me on X's MCQs", or wants to revise CS fundamentals, aptitude or output-prediction questions from past OAs.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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. Distinctive:

    If the user named a topic (OS, DBMS, networks, aptitude, output prediction, SQL), filter to it.

    line 15
  2. Very specific:

    Ask one question at a time: stem and options, with the number (e.g.

    line 22
  3. Distinctive:

    Default length 15 unless the user picks another.

    line 23
  4. Distinctive:

    Never reveal the answer before the user commits to one.

    line 24
  5. Distinctive:

    After each answer: correct or not, the right option, and a 1 to 3 line explanation.

    line 25
  6. Distinctive:

    Use the saved explanation when present.

    line 26
  7. Distinctive:

    If the saved key looks wrong, say so plainly with your reasoning instead of defending it.

    line 27
  8. Distinctive:

    Keep a running score. The user can say "stop" at any point.

    line 28

≈ “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.

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

MCQ drill

Part of oahelper-mcp by Sirjan Singh.

1. Load questions

  1. oahelper_offline(company). If there are no MCQ sets saved, oahelper_sync(company).
  2. MCQ answer keys live in the question files under library/<co>/questions/, in the ## MCQ answers section. Read those files; do not refetch.
  3. If the user named a topic (OS, DBMS, networks, aptitude, output prediction, SQL), filter to it. Otherwise draw from the newest sets first.
  4. Skip questions marked correct in library/_progress.md unless the user asks for a full pass.

2. Drill loop

  • Ask one question at a time: stem and options, with the number (e.g. Q4 of 15). Default length 15 unless the user picks another.
  • Never reveal the answer before the user commits to one. Accept letters or option text.
  • After each answer: correct or not, the right option, and a 1 to 3 line explanation. Use the saved explanation when present; otherwise write your own and say so.
  • If the saved key looks wrong, say so plainly with your reasoning instead of defending it.
  • Keep a running score. The user can say "stop" at any point.

3. Wrap up

Score: <correct>/<attempted>
Missed by topic: OS 2, DBMS 1, ...
Review these: Q3 (paging), Q9 (normal forms), ...

Append each attempt to library/_progress.md (date | company | ref | title | topic | result), creating it with that header if needed.

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.

Check your setup, free