agentleFS
q2522879285-sourceq2522879285-source/red-monkey-reasoning-kit/skills/dual-layer-explanation/SKILL.md

dual-layer-explanation

Skill2 starsChanged 2 months agoMITView on GitHub

Explain one concept at two aligned levels: a novice-friendly intuition and a technically accurate mechanism with boundaries. Use for teaching, mixed audiences, or requests for simple and professional versions plus comprehension checks. Skip pure translation, summarization, fixed instructions, and expert-only proofs that do not need a novice layer.

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Use when the user wants to learn a concept or mechanism, asks for both beginner and professional versions, has mixed prior knowledge, or …

    line 12
  2. Distinctive:

    Add up to three checks covering mechanism recall, boundary recognition, and transfer to a new case.

    line 22
  3. Very specific:

    Use $socratic-problem-framing first only if the learning target or misconception is unclear enough to change the explanation.

    line 26
  4. Very specific:

    Use $fact-claim-audit when the professional layer depends on current or disputed facts.

    line 27
  5. Distinctive:

    Never let an analogy replace safety-critical rules, legal conditions, medical constraints, or exact engineering limits.

    line 28

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dual-Layer Explanation

Own explanation structure and comprehension checks. Domain owners supply and verify the underlying facts.

Route

Use when the user wants to learn a concept or mechanism, asks for both beginner and professional versions, has mixed prior knowledge, or may confuse an analogy with the real mechanism.

Skip pure translation, summary, formatting, fixed operating instructions, or a request explicitly limited to a formal proof or expert definition.

Procedure

  1. Fix the target concept, audience baseline, and required depth.
  2. Give the novice layer: one plain-language intuition and one concrete example.
  3. Give the professional layer: precise terms, the causal or structural mechanism, applicable conditions, failure boundaries, and common misconceptions.
  4. Map each important part of the example to the professional variables and state where the analogy breaks.
  5. Add up to three checks covering mechanism recall, boundary recognition, and transfer to a new case. Reduce the count when less is enough.

Handoffs and Boundaries

  • Use $socratic-problem-framing first only if the learning target or misconception is unclear enough to change the explanation.
  • Use $fact-claim-audit when the professional layer depends on current or disputed facts.
  • Never let an analogy replace safety-critical rules, legal conditions, medical constraints, or exact engineering limits.

Completion Gate

Both layers describe the same mechanism. The analogy-to-term mapping and its breakpoints are explicit, the professional layer contains boundaries, and the checks distinguish remembering the story from understanding the mechanism.

Source Status

Distilled from the user-supplied “双层解释法” method card. The card proposes a teaching format but supplies no measured evidence that it improves learning or retention.

<!-- integration-watermark: 红猴子整合 -->

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.