agentleFS
SirjanSinghSirjanSingh/oahelper-mcp/skills/oa-mock/SKILL.md

oa-mock

Skill2 starsChanged 27 days agoMITView on GitHub

Run a timed mock online assessment for one company using real past questions saved by the oahelper MCP server, then grade it. Use when the user says "mock OA for X", "give me a practice test", "simulate X's assessment", "test me like the real OA", or wants timed practice before an upcoming OA.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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. Very specific:

    Read library/<co>/index.md and the newest 2 or 3 set files.

    line 14
  2. Distinctive:

    Prefer sets from the last 12 months.

    line 19
  3. Distinctive:

    Never show answers, official solutions or MCQ keys while the mock is running.

    line 20
  4. Distinctive:

    Ask them to paste code or answers, in any order, and to say "submit" when done.

    line 26
  5. Distinctive:

    Do not give hints during the mock.

    line 27
  6. Distinctive:

    Read their code against the statement.

    line 33

≈ “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

Mock OA from past questions

Part of oahelper-mcp by Sirjan Singh.

1. Build the paper

  1. oahelper_offline(company). If nothing is saved, run oahelper_sync(company) until it stops saying NOT DONE (or about 40 live requests, whichever comes first).
  2. Read library/<co>/index.md and the newest 2 or 3 set files. Copy the real format: number of coding vs MCQ questions, and the time limit if the sets or interview write-ups state one. If no time limit is known, use 90 minutes for 2 to 3 coding questions and 1 minute per MCQ, and say it is an assumption.
  3. Pick questions the user has not attempted (check library/_progress.md if it exists). Prefer sets from the last 12 months. Mix difficulties like the real sets do.
  4. Never show answers, official solutions or MCQ keys while the mock is running.

2. Run it

  • Tell the user the format, the number of questions and the end time, then show all questions at once like a real OA. Give statements, constraints and sample I/O only.
  • Ask them to paste code or answers, in any order, and to say "submit" when done.
  • Do not give hints during the mock. If they ask, remind them it is a mock and offer hints after submission.

3. Grade it

For each coding question:

  • Read their code against the statement. Trace it on the sample tests and on 2 or 3 edge cases you construct (empty input, max constraints, duplicates, negatives).
  • Verdict: likely accepted, wrong answer (show the failing case), or too slow (give the complexity and the constraint it breaks).
  • Fetch oahelper_solution only if the user asks for the official one; it may use quota.

For MCQs: compare to the saved answer key. For each miss, give the correct option and a one-line reason.

4. Report

Mock: <company>, <n> questions, <time used> of <time limit>
Score: <solved>/<coding>, <correct>/<mcq>
| # | Question | Topic | Result | Note |
Weakest topics: ...
Next: 2 or 3 concrete practice items

Append one row per question 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.