clear-explanation
Skill0 starsChanged 4 months agoMITView on GitHub
Explain complex ideas clearly for a specific audience using the CLEAR filter: Calibrate, Link, Envision, Abstract, Repeat. Use when user asks to \"explain this clearly\", \"simplify this\", \"translate this for non-technical stakeholders\", \"make this easier to understand\", \"explain this to a beginner\", or rewrite dense jargon into plain language.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- creative-writingSkill
- dataset-triageSkill
- excalidraw-system-sketchSkill
- figma-to-uiSkill
- frontend-designSkill
- mermaid-architecture-mapSkill
- newsletter-growthSkill
- no-ai-slopSkill
- outreach-emailSkill
- presentation-builderSkill
- resume-helperSkill
- skill-authoringSkill
- stanford-researchSkill
- technical-writingSkill
- verification-loopSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 13 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈13
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 13
Use for explanations, rewrites, teaching notes, stakeholder summaries, beginner-friendly descriptions, and jargon translation.
- Distinctive: line 15
Do not use for narrative craft, academic literature synthesis, outreach email, newsletter strategy, AI-pattern cleanup, or visual UI design …
- Distinctive: line 23
Must-keep terms, facts, caveats, or legal/security constraints.
- Distinctive: line 25
If audience missing, infer only when safe.
- Distinctive: line 38
If interactive, ask: "How familiar are they with this topic?" If not interactive, state assumed level.
- Distinctive: line 44
Use one analogy, metaphor, or familiar comparison when it reduces effort.
- Distinctive: line 56
Use one simple model:
- Distinctive: line 73
Prefer concrete nouns and active verbs.
- Distinctive: line 74
Keep one idea per sentence.
- Distinctive: line 75
Keep caveats that change decisions.
- Distinctive: line 76
Remove detail that does not help audience act or understand.
- Distinctive: line 78
Use this test: if listener could not repeat core idea after one hearing, simplify more.
- Distinctive: line 116
Use direct simple sentences.
≈ “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
Clear Explanation
Turn complex ideas into audience-fit explanations. Use CLEAR: Calibrate, Link, Envision, Abstract, Repeat.
Scope
Use for explanations, rewrites, teaching notes, stakeholder summaries, beginner-friendly descriptions, and jargon translation.
Do not use for narrative craft, academic literature synthesis, outreach email, newsletter strategy, AI-pattern cleanup, or visual UI design unless explanation clarity is main job.
Inputs
- Topic or draft.
- Audience and their familiarity.
- Desired channel: spoken, email, doc, slide, comment.
- Length limit, if any.
- Must-keep terms, facts, caveats, or legal/security constraints.
If audience missing, infer only when safe. Otherwise ask one calibration question.
Workflow
Step 1: Calibrate
Set audience level before explaining.
- Beginner: no jargon. Define needed terms.
- General professional: use common business/technical words.
- Specialist: keep field terms, remove needless complexity.
- Mixed audience: explain in layers, simple first, details after.
If interactive, ask: "How familiar are they with this topic?" If not interactive, state assumed level.
Step 2: Link
Connect unknown to known.
Use one analogy, metaphor, or familiar comparison when it reduces effort. Keep link close to audience world. Drop analogy if it hides important differences.
Pattern:
Think of [complex thing] like [known thing]. The important similarity: [shared structure]. The limit: [where analogy stops].Step 3: Envision
Make shape visible when words alone strain memory.
Use one simple model:
- 3-step flow.
- Before/after.
- Cause/effect chain.
- Small table.
- ASCII sketch.
- Named stages.
Skip visual model for short direct answers.
Step 4: Abstract
Boil idea to simplest useful form.
- Replace jargon with plain words unless audience needs exact term.
- Cut acronyms or define once.
- Prefer concrete nouns and active verbs.
- Keep one idea per sentence.
- Keep caveats that change decisions.
- Remove detail that does not help audience act or understand.
Use this test: if listener could not repeat core idea after one hearing, simplify more.
Step 5: Repeat
Close loop. Restate core idea in one line.
Use:
In short: [one-sentence takeaway].For longer explanations, end with what user should remember or do next.
Output Shape
Default:
- Assumption: audience level, if not supplied.
- Plain explanation: short, direct explanation.
- Link: analogy or comparison, if useful.
- Shape: model, steps, table, or diagram, if useful.
- In short: one-line takeaway.
For rewrite requests, return rewritten version first. Add short notes only when needed.
Quality Checks
- Audience level named or known.
- No needless jargon.
- Jargon kept only when useful and defined once.
- Analogy helps and includes limit if risk of overreach.
- Structure visible for complex ideas.
- Core idea repeatable in one sentence.
- Accuracy preserved over simplicity.
Writing
Use direct simple sentences. Skip rhetorical flourishes. Avoid X-not-Y contrasts, self-answering rhetorical questions, em dashes, alliterative three-part phrases, vague inspirational pivots, unsourced claims, and unverified quotes.
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.

