explain
Skill1 starsChanged 5 months agoMITView on GitHub
Explain any topic at the right depth — simple (plain language, one analogy) or deep (mechanisms, trade-offs, design decisions). Depth inferred from context or stated explicitly.
122 other projects use a version of this.
Adopted by
Most recently taken up by
- NazmusSayad/skillstheir own version, first seen Nov 8, 2026
- sergeiwallace/skillstheir own version, first seen Nov 8, 2026
- paulocsb/worldcup-fifa-pooltheir own version, first seen Nov 8, 2026
- whyashthakker/estacktheir own version, first seen Nov 8, 2026
- ShahriarBijoy/show-me-howtheir own version, first seen Nov 8, 2026
- nearmap/shipyardtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use debug-fix, root-cause and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
zebbernSkilldebug-fix
Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)
Also in 3 projects that use this
Ingramradical235Skillroot-cause
Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.
Also in 5 projects that use this
ralphkraussSkillresolve-conflicts
Resolve git merge conflicts or re-apply changes from a stale branch onto current main. Use when user says "resolve conflicts", "merge conflicts", "rebase branch", "branch is behind", "re-apply changes", "port branch", or a branch is too far behind main to merge cleanly.
Also in 4 projects that use this
neurofooSkillsocratic
Socratic questioning to examine beliefs, uncover assumptions, and develop deeper understanding. Use to challenge thinking, evaluate proposals, or teach without lecturing.
Also in 4 projects that use this
anombyte93Skilldiscover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.
Also in 6 projects that use this
mitsuhikoSkillsummarize
Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize
Also in 8 projects that use this
Other versions122 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 122
- Z3Prover/z3★ 13ksame name
- crbnos/carbon★ 2.8ksame name
- poshan0126/dotclaude★ 871same name
- VinkyDev/vibestart★ 289same name
- hsantanna88/clo-author★ 262same name
- hugosantanna/clo-author★ 262same name
- entireio/skills★ 239same name
- sammcj/agentic-coding★ 169same name
- SerhiiKorniienko/bullshit-detector★ 151same name
- kv0906/pm-kit★ 138same name
112 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-legalSkill
- audit-securitySkill
- echartsSkill
- file-changelogSkill
- file-claudeSkill
- file-licenseSkill
- file-projectSkill
- file-readmeSkill
- frontendSkill
- hooksSkill
- lean-reviewSkill
- loopSkill
- masterpromptSkill
- mcpSkill
- mermaidSkill
- new-projectSkill
- outputstyleSkill
- proofreadSkill
- rulesSkill
- settingsSkill
- skillsSkill
- sotaSkill
- subagentsSkill
- tasksSkill
- toonSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 109 edited versions we read keep these.
6
Distinctive
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 23
Never deliver simple mode when the question signals technical depth — and vice versa.
- Distinctive: line 24
Never omit the core mechanism in either mode.
- Distinctive: line 34
Never invent technical details not supported by actual knowledge of the topic.
- Distinctive: line 35
Always offer the other depth level at the end of the response.
- Distinctive: line 84
When signals are mixed or absent: deliver a top-down executive summary (2–3 sentences) and explicitly offer both modes: "Want the simple …
- Distinctive: line 98
Use one analogy that covers the core mechanism, not just surface features.
“Common” is measured: kept by at least 6 in 10 of the 109 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Explain
1§ Purpose
Deliver targeted explanations calibrated to the audience's knowledge level and the
question's depth signal. Two modes: simple (accessible, one core idea, one analogy)
and deep (mechanisms, internal structure, trade-offs, limitations). The mode is
inferred automatically or stated explicitly.
2§ Use when
- User asks "what is X", "how does X work", "explain X", or "why does X...".
- User requests a specific depth: "ELI5", "plain English", "simple", "deep dive", "technical explanation", "trade-offs".
- A topic needs to be explained to a mixed or unknown audience.
- User says "explain" without further qualification.
3§ Hard constraints
- Never deliver simple mode when the question signals technical depth — and vice versa.
- Never omit the core mechanism in either mode.
- In simple mode: use at most one analogy; stick to it; never switch to another.
- In simple mode: never infantilize or personify abstract concepts. The audience is an adult unfamiliar with the domain — simplified means domain-accessible, not childlike. No nursery metaphors, no humanizing of abstractions, no "imagine X is a little person who...". Use neutral, concrete analogies from adjacent domains.
- In deep mode: state prerequisites upfront; do not assume knowledge that was not signalled in the question.
- In deep mode: always include project context implications — how the concept's behavior, trade-offs, or limitations concretely affect the current project.
- Never invent technical details not supported by actual knowledge of the topic.
- Always offer the other depth level at the end of the response.
4§ Depth modes
4.1§ Simple
For lay audiences, executives, or anyone who signals plain-language intent.
Structure: core idea (1–2 sentences) → one neutral analogy (optional) → one example → why it matters → offer deep alternative.
Target: readable in under 30 seconds. Max 2–3 new terms, each immediately defined. Omit: trade-offs, edge cases, historical context, implementation detail.
Tone: clear and direct for adults — not simplified to the point of condescension. Concrete comparisons from adjacent domains are welcome; personification and nursery- style metaphors are not.
4.2§ Deep
For practitioners, implementers, or anyone who signals technical intent.
Structure: prerequisites → overview → how it works (mechanisms, 3–5 steps) → design decisions and trade-offs → concrete example → where it breaks down → project context implications → optional further depth pointer.
Target: complete enough that a practitioner can act on it. No jargon without definition; precision over brevity.
Project context implications: always state how the explained concept specifically affects the current project — which decisions it constrains, which risks it introduces, or which patterns it enables. Generic explanations without project anchoring are incomplete in deep mode.
5§ Context detection
Determine depth from the question before generating output.
Signals for simple mode:
- Lay vocabulary; no domain jargon.
- Question starts with "what is", "explain", "can you describe".
- Explicit markers: "ELI5", "simple", "plain English", "non-technical", "for a non-developer", "quick overview".
- Question has no follow-up technical qualifier.
Signals for deep mode:
- Question uses domain jargon correctly.
- Question asks "how does it work internally", "why does it fail", "what are the trade-offs", "how is it implemented", "how does it compare to X".
- Explicit markers: "deep dive", "technical", "internals", "edge cases", "details".
- Question is from a stated practitioner context.
When signals are mixed or absent: deliver a top-down executive summary (2–3 sentences) and explicitly offer both modes: "Want the simple version or the technical deep dive?"
Bloom's level heuristic — map the question's action verb:
- "What is / Explain" → simple (Understand).
- "How would I use" → simple + worked example (Apply).
- "Why does / How does it work" → deep (Analyze).
- "What are the trade-offs / Is X better than Y" → deep (Evaluate).
- "Design / What if we" → deep (Create).
6§ Explanation patterns
6.1§ Analogy rules
Use one analogy that covers the core mechanism, not just surface features. After the analogy, state explicitly where it breaks down — incomplete mental models are worse than no analogy. Avoid analogies when the concept has no stable equivalent in common experience (prefer first principles instead).
6.2§ Structure direction
- Top-down (overview first, then detail): use for simple mode and management contexts.
- Bottom-up (primitives first, then assembly): use for deep mode and implementer contexts.
6.3§ Chunking
Each chunk: one concept. Do not combine mechanism + trade-offs + example in the same paragraph. In deep mode: conceptual → mechanism → example → limits.
7§ Workflow
- Parse the question for depth signals (§5). Identify Bloom's level from the action verb. If ambiguous, state it and offer both modes.
- Identify what the person already knows from vocabulary and context — anchor the explanation one level above that, not from zero.
- Select mode (simple or deep) and structure direction (§6.2).
- In simple mode: draft core idea → choose one analogy → pick one example → state why it matters.
- In deep mode: state prerequisites → write overview → break mechanism into 3–5 steps → add trade-offs → write a concrete example → state where it breaks down.
- Append a one-line offer of the other depth level.
- Format the output following the in-chat template (§9). The templates define the chat output structure — output is written inline in the conversation, not to a file.
8§ Output contract
Must include:
- Core mechanism — present in both modes, never omitted
- Depth signal acknowledged (explicit or inferred) — state which mode is being used
- Offer of the other depth level at the end
- In deep mode: prerequisites stated upfront; trade-offs and at least one limitation
Must not include:
- Invented technical details
- Multiple analogies for the same concept in simple mode
- Jargon without definition in simple mode
- Assumed prior knowledge not signalled by the question in deep mode
9§ Associated documents
In-chat format templates — these define the structure Claude writes directly in the conversation, not file artifacts:
- [assets/explain-simple.template.md] — simple mode format.
- [assets/explain-deep.template.md] — deep mode format with project context section.
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.

