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

pretest

Skill0 starsChanged 5 days agoMITView on GitHub

Write 3 to 5 prequestions into a session note's Pretest section before the session, for the learner to guess first. Use when the learner is about to study a topic. Writes the questions only, so only run when asked.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are 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.

  • 3

    Very specific

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

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

    Write 3 to 5 questions into ## Pretest, from the simplest idea to the hardest.

    line 10
  2. Very specific:

    Leave My guess and After the session empty.

    line 11
  3. Distinctive:

    Do not reveal answers. After the session, the learner marks each guess right or wrong.

    line 12
  4. Very specific:

    Run run-checks after writing.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Tutor mode: the learner attempts first; the agent never writes the learner's guesses, the study layer or the answers.

  1. Open the session note (10_Tracks/<track>/sessions/) or ask for the topic and its sources. Read the syllabus, chapter titles, blueprint or transcript titles, not the full material.
  2. Write 3 to 5 questions into ## Pretest, from the simplest idea to the hardest. They cover what the session will teach, so most will be unanswerable now. That is the point.
  3. Leave My guess and After the session empty. Ask the learner to write a guess for each, with confidence from 1 to 5, before anything else. A wrong or blank guess is fine; looking it up is not.
  4. Do not reveal answers. After the session, the learner marks each guess right or wrong. Only then, on request, use the hint ladder (hint, strong hint, partial example, answer) for questions still open.
  5. Offer to turn missed questions into flashcards, written by the learner in their own words.

Run run-checks after writing.

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.