mcpField
T
teach

teach

github.com/yeachan-heoOther40.7k8 installsUpdated today
Repository

About teach

teach is a learning skill for explaining software subsystems in a learner-paced sequence. It combines a code walkthrough with evidence-based design rationale and a prediction check.

Key features

  1. 01Baseline-based explanation depth
  2. 02Code walkthrough with file and line citations
  3. 03Evidence for design decisions
  4. 04Prediction check to assess understanding

Use cases

  1. 01Introducing a subsystem to a learner
  2. 02Explaining why code is structured a certain way
  3. 03Checking whether a learner can predict behavior

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill teach

After installing, type/teachin Claude Code to confirm it loaded.

Details

From the project README

Teach

Teaching is how and why composed for a learner: what the subsystem does and the reasons it is shaped that way, in an order a person can absorb.

Workflow

  1. Ask the learner's baseline: one question — familiar with the domain, the language, or neither. Size the explanation to the answer.
  2. How first (how skill): the walkthrough, entry to exit, cited to file:line, at the depth the baseline supports.
  3. Then why (why skill): the 2-4 decisions that shaped it, each with its evidence and the alternative it beat. Human rulings quoted verbatim.
  4. Check the landing: ask the learner to predict one behavior — "if X happens, what does the subsystem do?" A correct prediction ends the lesson; a wrong one names the layer to redo. The check is for pacing, not grading.

Rules

  • One new concept per paragraph; jargon defined at first use in one clause.
  • Cite code for behavior, cite records for reasons; label anything you inferred.
  • Stop when the learner can predict behavior — completeness is not the goal, transfer is.

Comments

Markdown supported