agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/quiz/SKILL.md

quiz

Skill0 starsChanged 5 days agoMITView on GitHub

Write a quiz into 50_Review/Quizzes from the vault's own sources (concept, reference and session notes), with the answer key kept apart and revealed only after the learner answers and rates confidence. Use when the learner asks to be quizzed on a track or topic. Writes a file, so only run when asked.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use progress, learn and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • remenoscodesSkill

    progress

    Longitudinal language learning progress report with metrics, trends, and insights

    Also in 4 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 4 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 4 projects that use this

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 14 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. Distinctive:

    Read each concept's study layer and the references it cites.

    line 11
  2. Very specific:

    Write 50_Review/Quizzes/<Topic>_YYYY-MM-DD.md with type: review, a ## Questions section and a ## Answer key section inside a folded callout …

    line 12
  3. Distinctive:

    If the quiz file is not approved, ask the same questions in chat, one at a time, with the same rules.

    line 16

“Common” is measured: kept by at least 6 in 10 of the 14 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

Tutor mode: the learner answers first and rates confidence from 1 to 5 before any answer is shown. The agent never writes the learner's answers.

  1. Read the record first (50_Review/Attempts.jsonl, the concept scores, 50_Review/Mistakes.md). A concept with clean recalls and no application attempt gets an application question in a case the learner has not seen, plus one line on what counts as applying it, never the definition again. A concept with a low score or an open mistake starts easier.
  2. Pick 5 to 10 concepts for the track or topic, weakest and least recently tested first (calibration_report.py, Progress.base). Mix categories.
  3. Read each concept's study layer and the references it cites. Every question comes from a note in the vault and names it; never from memory.
  4. Write 50_Review/Quizzes/<Topic>_YYYY-MM-DD.md with type: review, a ## Questions section and a ## Answer key section inside a folded callout (> [!answer]- Answer key). Order: open recall questions first, then application, then at most a few multiple-choice questions whose wrong options are real misconceptions, not jokes. No hints inside the questions.
  5. Each question has an empty My answer: line and Confidence (1 to 5):. Leave them for the learner.
  6. Show nothing from the key until the learner has answered and rated confidence. Then grade against the source and a rubric: fluent but empty gets no credit, short and correct gets full credit, right answer for the wrong reason gets part.
  7. For each miss, offer mistake-review. Ask the learner whether to log the score in the concept (score, confidence, last_tested); set it only with their yes.
  8. If the quiz file is not approved, ask the same questions in chat, one at a time, with the same rules.

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.