grandma
Skill12 starsChanged 8 months agoMITView on GitHub
Explain technical concepts using everyday analogies that a grandma or 5-year-old could understand.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- add-testsSkill
- best-practiceSkill
- bootstrapSkill
- briefSkill
- changesSkill
- claude-code-reviewSkill
- claude-plan-reviewSkill
- codex-code-reviewSkill
- codex-plan-reviewSkill
- commit-pushSkill
- depsSkill
- design-researchSkill
- designSkill
- doc-driftSkill
- doc-syncSkill
- doc-tidySkill
- executeSkill
- explainSkill
- full-briefSkill
- goSkill
- planSkill
- post-design-reviewSkill
- recordSkill
- self-reviewSkill
- tech-researchSkill
- testSkill
- timelineSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Understand the topic: If it's a project module, quickly read design docs and core code to understand what it actually does
- Distinctive: line 15
If the concept has multiple layers, use different roles/stages within the SAME scenario — don't switch scenarios
- Distinctive: line 17
Start with the scene: "Imagine you're at..."
- Distinctive: line 19
After the analogy, "translate" back in one sentence: "What we just called X is actually Y in the code"
- Distinctive: line 22
Use technical jargon (unless the user is asking what a specific term means)
≈ “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.
Files
Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).
Arguments: $ARGUMENTS — any technical concept, module, or design decision (e.g., "ECS", "why does the task system use a push model", "what is MCP", "A* pathfinding algorithm")
Behavior
- Understand the topic: If it's a project module, quickly read design docs and core code to understand what it actually does
- Find an everyday life analogy that:
- Uses a scenario everyone has experienced (cooking, queuing, moving house, school, grocery shopping...)
- Covers the core mechanism, not just a surface similarity
- If the concept has multiple layers, use different roles/stages within the SAME scenario — don't switch scenarios
- Explain the entire concept through the analogy:
- Start with the scene: "Imagine you're at..."
- Map each role and action in the scene to key parts of the technical concept
- After the analogy, "translate" back in one sentence: "What we just called X is actually Y in the code"
- If there are common misconceptions, address them: "Many people think... but actually..."
- Don't:
- Use technical jargon (unless the user is asking what a specific term means)
- Show code
- Say "simply put" followed by something not simple
- Say "it's like in programming..." — the audience doesn't know programming, that's not an analogy
- Be condescending ("this is basic", "you can think of it as")
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
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.

