Claude Skill

eli5

Applies the house explanation style: concrete terms, optional analogy, no minimizers or promotional vocabulary, and verbatim technical identifiers. Use when asked for "ELI5", "plain English", "re-pitch that", or "stop using jargon". For product copy use copywriting; for documenta

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download mblode-agent-skills-skills_eli5-24f4fd8.zip · 1 KB

mblode/agent-skills 123 11 forks MIT Updated 5d ago

Part of mblode/agent-skills — 22 skills

Install

skills CLI npx skills add https://github.com/mblode/agent-skills/tree/main/skills/eli5

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install mblode-agent-skills@llmmart

Git git clone https://github.com/mblode/agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole mblode/agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Plain-language house style

Use this style for the explanation requested. Keep it for later replies only when the user asks for an ongoing mode; a single ELI5 request does not change the session permanently.

Preserve exact identifiers, paths, commands, errors, numbers, and quoted source text. Explain around them.
Avoid minimizers: simply, obviously, just, easy, of course, as you know.
House vocabulary excludes promotional uses of: delve, leverage, robust, seamless, holistic, paradigm, game-changing, cutting-edge, innovative, synergy, revolutionary, effortless, world-class, powerful, showcase, unlock. Do not ban literal technical uses or quotations.
No em dashes in authored prose. Do not substitute a spaced hyphen.
Use an analogy only when it clarifies the mechanism; identify its limit if that affects the answer. If an explanation did not land, change the framing instead of making the same analogy longer.
Put the explanation or result first. Include a next action only when the reader needs to act. Do not assign the user work the agent is already authorized to complete.

Return the explanation itself. No activation announcement, fixed sentence count, compulsory recap, or pre-send checklist.

Boundaries

This changes assistant prose. Product copy belongs to copywriting, technical docs to docs-writing, README structure to readme-creator, and PR bodies to pr-creator.

Maintenance

evals/evals.json contains behavior and routing scenarios for changes to this skill; do not load it during an explanation.

Files (agent-skills)

evals

evals.json 1.5 KB

{
  "skill_name": "eli5",
  "evals": [
    {
      "id": 1,
      "prompt": "ELI5 what a JWT is. Keep it specific enough that I can recognize the term in our code.",
      "expected_output": "An explanation preserving JWT, without an activation announcement or mandatory follow-up.",
      "files": [],
      "assertions": [
        "Keeps JWT verbatim",
        "Does not promise encrypted contents merely because a token is signed",
        "Does not announce a permanent mode change"
      ]
    },
    {
      "id": 2,
      "prompt": "Explain this error in plain English: auth.ts:42 returned 401. Keep the command curl --header \"Authorization: Bearer $TOKEN\" intact.",
      "expected_output": "Explains the failure while preserving the supplied identifiers and command.",
      "files": [],
      "assertions": [
        "Preserves auth.ts:42 and 401",
        "Preserves the quoted command including $TOKEN",
        "Does not replace a technical token to satisfy a word ban"
      ]
    },
    {
      "id": 3,
      "prompt": "Keep plain English on for the rest of this session. Continue the migration you are already authorized to complete.",
      "expected_output": "Continues authorized work with the requested style.",
      "files": [],
      "assertions": [
        "Does not delegate its own work back to the user through a compulsory Next line",
        "Does not claim persistence across unrelated sessions",
        "Does not repeat activation announcements"
      ]
    }
  ]
}

SKILL.md 1.9 KB

---
name: eli5
description: "Applies the house explanation style: concrete terms, optional analogy, no minimizers or promotional vocabulary, and verbatim technical identifiers. Use when asked for \"ELI5\", \"plain English\", \"re-pitch that\", or \"stop using jargon\". For product copy use copywriting; for documentation use docs-writing."
---

# Plain-language house style

Use this style for the explanation requested. Keep it for later replies only when the user asks for an ongoing mode; a single ELI5 request does not change the session permanently.

- Preserve exact identifiers, paths, commands, errors, numbers, and quoted source text. Explain around them.
- Avoid minimizers: simply, obviously, just, easy, of course, as you know.
- House vocabulary excludes promotional uses of: delve, leverage, robust, seamless, holistic, paradigm, game-changing, cutting-edge, innovative, synergy, revolutionary, effortless, world-class, powerful, showcase, unlock. Do not ban literal technical uses or quotations.
- No em dashes in authored prose. Do not substitute a spaced hyphen.
- Use an analogy only when it clarifies the mechanism; identify its limit if that affects the answer. If an explanation did not land, change the framing instead of making the same analogy longer.
- Put the explanation or result first. Include a next action only when the reader needs to act. Do not assign the user work the agent is already authorized to complete.

Return the explanation itself. No activation announcement, fixed sentence count, compulsory recap, or pre-send checklist.

## Boundaries

This changes assistant prose. Product copy belongs to `copywriting`, technical docs to `docs-writing`, README structure to `readme-creator`, and PR bodies to `pr-creator`.

## Maintenance

`evals/evals.json` contains behavior and routing scenarios for changes to this skill; do not load it during an explanation.