explain · serhiikorniienko — Claude Code skill: what it does, how to install
explain breaks down concepts from code, docs or articles at the depth you need: analogies for beginners, mechanisms for practitioners, or full deep-dives.
MIT ★ 164 updated 2026-09-29
npx skills add SerhiiKorniienko/bullshit-detector --skill explain -a claude-codeWhat explain does
The skill fetches text (loads URLs via fetch-content or takes pasted content), picks a depth level (ELI5, practitioner, or deep dive with mechanisms and history), and builds the explanation. Every explanation starts with a one-sentence summary, then walks through the mechanism step by step, provides a glossary of jargon the original did not define, and lists the prerequisites the content assumed you knew. When the source oversimplifies or gets something wrong, the skill flags it.
Triggers include "explain this", "what does X mean here", "break this down", or sharing a fragment and asking how it works. Analogies are tested: if the metaphor breaks, the skill tells you where. Works in Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode; install via npx skills add with a platform flag.
What it helps with
- unpack a concept from an article, video or docs without hunting for context
- get a glossary of jargon the author left undefined
- see where an analogy or simplification stops holding
- understand what the text assumes you already know
- choose explanation depth: from metaphor to full mechanism with edge cases
Example prompts for the agent
- Explain what
RefCelldoes in this code - Break down the mechanism in section 3 of the docs
- What does 'batching' mean in this fragment?
How to install explain
1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill explain -a claude-code2Manually: put the files in place
~/.claude/skills/explain/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/explain/
1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill explain -a codex2Manually: put the files in place
.agents/skills/explain/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill explain -a cursor2Manually: put the files in place
.cursor/skills/explain/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SerhiiKorniienko/bullshit-detector skills/analysis/explain2Manually: put the files in place
.github/skills/explain/SKILL.md1Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill explain -a gemini-cli2Platform CLI
gemini skills install https://github.com/SerhiiKorniienko/bullshit-detector --path skills/analysis/explainManually: put the files in place
.devin/skills/explain/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add SerhiiKorniienko/bullshit-detector --skill explain -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about explain
How to install explain in Claude Code?
Run npx skills add SerhiiKorniienko/bullshit-detector --skill explain -a claude-code. The skill lands in ~/.claude/skills/explain/SKILL.md.
What does explain do?
Breaks down concepts from code, docs or articles at the depth you choose, provides a jargon glossary and lists the prerequisites the content assumed. Flags where the source oversimplifies or errs.
What depth levels does explain support?
Three: ELI5 (analogies, no jargon), practitioner (how it works and what to do with it), and deep dive (mechanisms, edge cases, history).
Source text
SKILL.md · MIT
---
name: explain
description: Explain content or any concept inside it at the depth the user needs — ELI5, practitioner level, or expert deep-dive — with a jargon glossary and context the original assumes. Use when the user says "explain this", "what does X mean here", "break this down", "I don't understand this part", or shares content and asks how something in it works.
---
# explain
Make the content understandable without dumbing it down dishonestly.
## Workflow
1. **Get the text** (via `fetch-content` skill script if it's a URL, else web fetch or paste).
2. **Pick the depth** — from the user's request, or ask one short question if genuinely unclear:
- **ELI5** — analogies, zero jargon, the core mechanism only
- **Practitioner** — assumes general technical literacy, focuses on how it works and what to do with it
- **Deep dive** — mechanisms, edge cases, history, competing views
3. **Explain**, structured as:
- The one-sentence version first
- The mechanism: how it actually works, step by step
- **Glossary**: every jargon term the content uses without defining, one line each
- **What the content assumes you know** — the missing prerequisites that made it confusing
- Where the content's own explanation is wrong or oversimplified, if it is — flag it, don't repeat it
## Rules
- Explaining ≠ endorsing. If the content's claim is contested, present the explanation *and* note the contest ("the video asserts X; the standard view is Y").
- Analogies must survive scrutiny — say where the analogy breaks.
- If the user points at a specific segment ("the part at 12:30", "section 3"), explain that segment in the context of the whole, not in isolation.
- Don't pad: a concept that takes three sentences gets three sentences.
© SerhiiKorniienko · MIT · SerhiiKorniienko/bullshit-detector
Similar skills
All skills for Writing and docs →explain by other authors comes first.