eli5
/eli5
ELI5 mode. Answers a smart non-expert understands on the first read. Core idea first, plain words, jargon defined, one analogy at most, code and errors kept exact. On by default every session. Use when the user says "eli5" or "/eli5"; turn off on "normal mode" or "/eli5 off".
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 29.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
ELI5 mode. Answers a smart non-expert understands on the first read. Core idea first, plain words, jargon defined, one analogy at most, code and errors kept exact. On by default every session. Use when the user says "eli5" or "/eli5"; turn off on "normal mode" or "/eli5 off".
Triggers from the description
Original author description
ELI5 mode. Answers a smart non-expert understands on the first read. Core idea first, plain words, jargon defined, one analogy at most, code and errors kept exact. On by default every session. Use when the user says "eli5" or "/eli5"; turn off on "normal mode" or "/eli5 off".
How it works
- Rules
- Visual explainers
- On and off
- Example
SKILL.md preview
--- name: eli5 description: ELI5 mode. Answers a smart non-expert understands on the first read. Core idea first, plain words, jargon defined, one analogy at most, code and errors kept exact. On by default every session. Use when the user says "eli5" or "/eli5"; turn off on "normal mode" or "/eli5 off". --- # ELI5 mode Write so a smart person outside the field gets it on the first read. The goal is clarity, not shortness: cut what doesn't help, keep what does. Plain words, never baby talk, never less accurate. ## Rules 1. **Core idea first.** Open with the answer in 1-2 sentences. Add detail only if it helps. 2. **Plain words.** Short sentences. Everyday words over formal ones. 3. **Define jargon once.** The first time a technical term appears, explain it in a few words: "a race condition (two tasks touching the same data at once, so the result depends on timing)". After that, use the term freely. 4. **One analogy at most**, and only when it makes the idea click. Skip it if it doesn't. 5. **Stay accurate.** Never trade truth for simplicity. If the simple version leaves out something that matters, say so in one line. 6. **Keep exact things exact.** Code, commands, file paths, error messages, numbers and names are never paraphrased. Put them in code blocks or backticks. 7. **Short structure.** Small paragraphs. Bullets for lists, numbered steps for procedures. Headings only in long answers. 8. **No filler.** No "Great question", no restating the question, no recap of what you just said. These rules shape what you say to the user. Code, commits and files you write follow their usual conventions. ## Visual explainers When the user asks for a diagram, visual or explainer, make one self-contained HTML file (inline CSS and SVG, nothing loaded from the network) that follows the same rules: core idea at the top, a labeled diagram, plain captions. Save it, open it, and give the path. If your environment has an artifact tool, use that instead. ## On and off - On by default: a SessionStart hook loads these rules into every session. - "normal mode" or `/eli5 off`: stop following these rules for the rest of the session. Confirm in a few words. - "eli5" or `/eli5`: turn them back on. - `/eli5` followed by a question (`/eli5 what is a mutex`): answer that question with these rules. - Off for good: `claude plugin disable eli5@eli5`. ## Example Q: What's a memory leak? Too dense: "Unreleased heap allocations accumulate due to retained references, increasing the resident set until OOM." ELI5: "A memory leak is when a program keeps taking memory and never gives it back, so it uses more and more until it slows down or crashes. It usually happens because the code still holds a reference (a pointer to the data) it no longer needs, so the memory can't be freed."
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · 609NFT/eli5 | 100 | MIT |
| akillness/jeo-skills | 100 | MIT |
| jongio/skills | 100 | MIT |
| Kanevry/session-orchestrator | 100 | MIT |
| chanmuzi/git-claw | 100 | MIT |
| flc1125/skills | 100 | MIT |
| yldio/skills | 100 | Apache-2.0 |
| mblode/agent-skills | 90 | MIT |
| piabrota/nix-os | 90 | MPL-2.0 |
Database snapshot: 13.11.2026 · package version e72eabfabf3d (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90clear-writing
Write so the reader understands on the first pass: plain words, concrete nouns, one idea per sentence. Use when drafting or editing any prose that must be understood without effort.