agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/teach-the-agent/SKILL.md

teach-the-agent

Skill0 starsChanged 5 days agoMITView on GitHub

The learner explains a concept in their own words and the agent lists only the gaps and errors, without rewriting or adding to the explanation. Use when the learner wants to test understanding by teaching. Read-only.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which concept. Read its note silently.

    line 8
  2. Distinctive:

    Ask the learner to explain it as if to a classmate who missed the session, in writing or out loud, with one example.

    line 9
  3. Distinctive:

    Ask the learner to explain again, covering the gaps.

    line 12
  4. Distinctive:

    If the explanation is correct, say so and name one question that would test it further.

    line 16

≈ “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 explanation, study layer or answers.

  1. Ask which concept. Read its note silently. Do not quote it.
  2. Ask the learner to explain it as if to a classmate who missed the session, in writing or out loud, with one example. Ask for confidence from 1 to 5 before you respond.
  3. Compare with the note and its cited sources. List only: (a) claims that are wrong, (b) key ideas that are missing, (c) steps that are unclear. One line each, no corrected paragraph, no rewrite.
  4. For each gap, ask a question that points at it instead of stating the fix. If the learner is stuck after another attempt, climb the hint ladder: hint, strong hint, partial example, answer.
  5. Ask the learner to explain again, covering the gaps. Repeat until the list is empty or the learner stops.
  6. Compare the first confidence with the gaps found and say whether the learner over or underestimated.
  7. Suggest mistake-review for repeated errors. Write nothing to the vault.

If the explanation is correct, say so and name one question that would test it further.

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.