agentleFS
Sign inStart free
kidowkidow/skills/place-me/SKILL.md

place-me

Skill2 starsChanged 6 months agoMITView on GitHub

Run a short adaptive diagnostic to gauge how much the user already knows about a topic before learning it, then save a prose level summary to a single git-tracked levels.md. Use when the user is about to learn a topic and wants a level check first, asks to be tested on what they know, or says "place me".

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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. Distinctive:

    No topic given → ask which topic to test.

    line 10
  2. Very specific:

    Before testing, read levels.md at the repo root if it exists.

    line 12
  3. Distinctive:

    Ask one question about the topic.

    line 16
  4. Distinctive:

    Read my answer. Judge whether it was below, at, or above the difficulty you just probed.

    line 17
  5. Distinctive:

    Stop as soon as you are confident about my level — there is no fixed question count.

    line 20
  6. Distinctive:

    When confident, persist the result:

    line 26
  7. Distinctive:

    Check git rev-parse --is-inside-work-tree.

    line 28
  8. Very specific:

    Write to a single unified file levels.md at the repo root (git-tracked, no date in the name):

    line 29
  9. Distinctive:

    If a section for this topic exists, update it in place.

    line 37
  10. Very specific:

    Commit just that file: place: <topic_name> level assessment.

    line 38
  11. Distinctive:

    After saving, hand off to teach-me for the same topic, telling it to calibrate to the level summary just written.

    line 42

≈ “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

Find out how much I already know about a topic before teaching me. Companion to teach-me: place-me sizes me up, teach-me then teaches at the right level.

Topic

  • No topic given → ask which topic to test. Stop and wait.
  • Context given but not a concrete topic → ask me to name a specific topic. Stop and wait.
  • Before testing, read levels.md at the repo root if it exists; use any prior summary for this topic as a starting guess.

Test loop

  1. Ask one question about the topic. Stop and wait.
  2. Read my answer. Judge whether it was below, at, or above the difficulty you just probed.
  3. Adapt: if I answered easily, go harder; if I struggled, go easier.
  4. Repeat, one question at a time, never two at once.
  5. Stop as soon as you are confident about my level — there is no fixed question count. Don't drag it out once the signal is clear.

Match the question language to the language I gave the topic in.

Saving the level (only if the working folder is a git repo)

When confident, persist the result:

  1. Check git rev-parse --is-inside-work-tree. If not a repo, just tell me the result — do not save or commit.
  2. Write to a single unified file levels.md at the repo root (git-tracked, no date in the name):
    • One ## topic_name section per topic.
    • Content: open with one of four level labels, then a prose summary of what I clearly know, what I'm shaky on, and what I don't know yet.
      • Blank — no prior exposure to the concept.
      • Glimpsed — seen it before but cannot reproduce or explain it reliably.
      • Grounded — explains it independently and applies it correctly in new contexts.
      • Fluent — handles exceptions, nuance, and edge cases without hesitation.
    • Example: Level: Grounded — Knows X and Y, applies them correctly, shaky on Z, hasn't encountered W yet.
    • If a section for this topic exists, update it in place; never duplicate.
  3. Commit just that file: place: <topic_name> level assessment.

Handoff

After saving, hand off to teach-me for the same topic, telling it to calibrate to the level summary just written.

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