Skip to content
Get packs

ljg-explain: Teach Concepts Until Usable

Explains concepts, formulas and mechanisms so you can recognise, reason about and apply them in new cases.

Source Download skill
Repository
lijigang/ljg-skills
Stars
7,607
Licence
MIT
Files
2 files

What it does

When you ask the agent to explain an idea, formula or mechanism, it follows a set of rules for teaching so you can actually use the knowledge, not just repeat it. It starts from a real question, shows examples and near-miss contrasts, walks through how the parts cause the result, shows how the answer changes when one condition changes, and then applies the idea to a different situation. It is a writing guide for the agent, with no code or external services involved.

Great for

  • Learners who want to understand a concept well enough to use it in a new situation
  • Students preparing to explain statistics, maths or science ideas in plain language
  • Anyone who wants a clear, conversational Chinese-language explanation of a principle

Skip it if

  • Simple proofreading, polishing or translation, since the skill is designed for teaching rather than editing (the skill itself says so)
  • Reading or summarising a whole book or paper, which it explicitly excludes
  • Users who need only a formal proof or step-by-step procedure without intuition, also excluded by the skill's own description

Try asking

  • “ljg-explain the variance formula, and show me what each step means with real numbers”
  • “Explain Bayesian likelihood versus posterior probability using one example, and say what each one answers”
  • “Explain positive feedback loops in plain Chinese and then apply the idea to a different system”
  • “ELI5 how compound interest works, and show what changes if the rate doubles”
Step-by-step guide: how to use ljg-explain: Teach Concepts Until UsableInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    ljg-explain.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ljg-explain.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ljg-explain.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the concept and say what you already know, so the explanation starts at the right level
  • Ask for a specific example from your own field, which makes the transfer step more useful
  • Check any numbers the agent produces in an example, since it may use invented teaching figures that it should label as assumptions

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from lijigang/ljg-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.