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

visual-reconstruction

Skill0 starsChanged 5 days agoMITView on GitHub

Check a diagram, map or flow the learner drew from memory, list only the relations that the source has and the drawing does not, and ask a question about each one; use it when the learner asks to check a diagram they drew, and it writes a note, so run it only when asked.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which concept and which drawing.

    line 12
  2. Very specific:

    Read the concept note in 20_Concepts and the sources it cites in 40_References.

    line 14
  3. Distinctive:

    Read the learner's drawing.

    line 16
  4. Distinctive:

    Never skip a step.

    line 25
  5. Distinctive:

    Ask for confidence from 1 to 5 before the reveal.

    line 26
  6. Very specific:

    Write the practice note from 90_System/Templates/Visual_Reconstruction.md into the practice folder of the track the concept belongs to: …

    line 28

≈ “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, and the drawing is the attempt. The agent never writes the learner's notes or answers and never draws the diagram for them. Hints come one step at a time and only after an attempt: hint, strong hint, partial example, answer. Confidence from 1 to 5 is asked before the reveal. The agent never grades an attempt the learner did not confirm.

  1. Ask which concept and which drawing. The drawing is a canvas file or a list of relations the learner wrote.
  2. Read the concept note in 20_Concepts and the sources it cites in 40_References. Build the reference relations from those sources: what points at what, and in which direction.
  3. Read the learner's drawing. Compare it with the reference relations.
  4. List only what is missing: the relations that are in the source and not in the drawing. One line per missing relation. Do not list what is right, do not praise the drawing and do not rewrite it.
  5. The agent never redraws the diagram and never adds the missing relation itself. For each missing relation, ask the learner a question about it. The question points at the relation without giving it away.
  6. Let the learner answer. Then, and only then, reveal the missing relation. If the answer is wrong, use the hint ladder one step at a time: hint, strong hint, partial example, answer. Never skip a step.
  7. Ask for confidence from 1 to 5 before the reveal. Then grade the learner's words against the source and the rubric.
  8. Write the practice note from 90_System/Templates/Visual_Reconstruction.md into the practice folder of the track the concept belongs to: 10_Tracks/<NN>_<Track>/practice/Visual_Reconstruction.md. Fill the Date, Concept, What I drew, Relations kept, Relations missing and Question it left open columns. Write the note only after the learner confirms it.
  9. Record the attempt after the learner confirms the result. The mode is explain.
python3 -I 90_System/Scripts/record_attempt.py --objective <id> --item <id> --mode explain \
  [--correct|--incorrect] --confidence <1-5> [--hints <n>] [--assistance <level>]
  1. A drawing that keeps the nodes but loses an arrow has not kept the idea. Say that in one line when a relation is missing.
  2. Show the learner the line that was written. Never edit or delete a line of the ledger.

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.