Skip to content
Get packs

Analogy Finder (ljg-analogy)

Builds clear, structure-preserving analogies to explain a scene or contrast two things

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

What it does

When installed, the agent answers 'explain this by comparison' requests by finding a familiar everyday scene whose relationships match the one you want to understand, then walks through how the parts map onto each other and where the comparison breaks down. It is designed to avoid shallow 'X is like Y' lines, to compare two things using a shared framework, and to flag what the analogy cannot prove. It works from written instructions alone and does not run code or access the internet for ordinary analogies.

Great for

  • Writers or teachers who need a memorable way to explain a concept
  • People trying to understand the difference between two tools, products or mechanisms
  • Anyone who wants a single, well-reasoned metaphor rather than a list of loose comparisons

Skip it if

  • Checking facts or proving a claim: the skill itself says analogies suggest possibilities and cannot establish that something is true, so do not use them as evidence in a decision
  • Simply explaining an existing famous metaphor or polishing prose style, which the skill explicitly excludes
  • Sensitive social or political questions, where a neat analogy could imply a false inevitability about people's behaviour or motives

Try asking

  • “Find a good analogy for why my codebase's caching layer is hard to debug”
  • “Explain the difference between a mutual fund and an ETF using a everyday analogy”
  • “Give me one metaphor for what it feels like to return to a hometown after years away”
  • “Compare two project management methods in a way a non-technical manager would grasp”
Step-by-step guide: how to use Analogy Finder (ljg-analogy)Install, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    ljg-analogy.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ljg-analogy.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

  • State the specific relationship you want to understand (who affects whom, what constrains what), not just the topic, so the analogy targets the right structure
  • Ask for a comparison of two things explicitly if you want differences highlighted, and say your audience if it is not the general public
  • Verify any factual claims the analogy depends on independently, since the skill notes that facts should be checked with current sources when uncertain

What's inside

  • agents/openai.yaml
  • EvalCases.json
  • SKILL.md
  • Theory.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.