agentleFS
Sign inStart free
Catherine1401Catherine1401/agent-skills/skills/quizz/SKILL.md

quizz

Skill2 starsChanged 54 days agoMITView on GitHub

Convert a multiple-choice question bank with an answer key (PDF, DOCX, or similar) into Wayground (Quizizz) import spreadsheets built from the bundled Wayground template. Use when asked to create Wayground/Quizizz quizzes or import files from a question bank.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Use only Multiple Choice (one correct answer) and Checkbox (several correct answers).

    line 6
  2. Distinctive:

    When the user supplies a template, confirm its columns A–K are: Question Text, Question Type, Option 1–5, Correct Answer, Time in seconds, …

    line 13

≈ “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
  • Use only Multiple Choice (one correct answer) and Checkbox (several correct answers).
  • Take correct answers only from the source's answer key; never decide answers yourself. If the source has more than one key (e.g. summary table and per-question explanations), cross-check them and report mismatches instead of picking one.
  • Source layouts differ per file: inspect the source and write a one-off extractor for it in a temp directory (pdftotext for PDF, python-docx or pandoc for DOCX); do not reuse a previous source's extractor unchecked. Strip page headers/footers and section titles that leak into question or option text.
  • Extract to JSON: [{"num", "text", "options": [2-5 strings in source order], "correct": [0-based indices], "explanation": string|null}]. Explanation = the source's explanation without the restated answer.
  • scripts/write.py <json> <out_dir> <prefix> [template.xlsx] copies assets/template.xlsx (or the user's newer template when given) (keeps header, instruction row 2, dropdowns), puts correct options first in source order (Correct Answer 1 or 1,2,...,N), wrong options after in source order, time 30s, 50 questions per file named <prefix>_<first>-<last>.xlsx.
  • scripts/check.py <json> <out_dir> <prefix> must report every file bad [] and coverage complete: True.
  • check.py only proves the xlsx matches the JSON. Before reporting success, also verify the JSON against the source: question count equals the source's count, every question has its answer from the key, and no header/footer text remains.
  • When the user supplies a template, confirm its columns A–K are: Question Text, Question Type, Option 1–5, Correct Answer, Time in seconds, Image Link, Answer explanation. Default output directory: current working directory.

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