# ceo

Use only when Austin explicitly invokes /ceo or $ceo. Explain status, systems, or technical work in concise plain English focused on outcomes, cost, risk, and time. This is an explanation mode, not a decision framework; do not manufacture options or prescribe a course of action unless Austin separately asks what to do. Ordinary requests for an explanation or summary must not activate it.

Kit: [working-style](https://atlasscope.dev/kits/working-style)

Written for Agent Kit. License: MIT, © AtlasScope.

## Install

```sh
npx skills add AtlasScope/agent-kit --skill ceo
```

Claude Code:

```sh
claude plugin marketplace add AtlasScope/agent-kit
claude plugin install working-style@agent-kit
```

## SKILL.md

# /ceo: explain, don't decide

`ceo` answers "what is happening, what does it mean, what should I know?" Use `/recommend` when Austin wants a chosen path.

Register: engineer reporting to a time-poor CEO. Outcomes, cost, risk and time, not code. No jargon without a ≤5-word translation on first use. No file paths, hashes, or PR numbers unless he must click them. Analogies are fine.

## Shape

```
**Bottom line:** [one sentence]

[Optional 2–3 sentences of plain English]

**Decisions you need to make:** [only if real]
**Risks worth knowing:** [only if material]
```

Strip unused sections. Routine updates are the bottom line plus one paragraph. If you are reaching a third subheading, cut.

If Austin asks for code, SQL, or deploy steps mid-thread, answer that one question as an engineer, then return to this register.

Do not invent a recommendation. If he asks "what should we do?", tell him to invoke `/recommend` or answer only that question without dragging `/ceo` into a decision framework.

Other files in the skill folder: agents. Browse them at https://github.com/AtlasScope/agent-kit/tree/main/kits/working-style/plugins/working-style/skills/ceo

Source: https://atlasscope.dev/skills/ceo