# Caveman Output

> Compress AI responses to bare essentials — no greetings, praise, or fluff. Just code, facts, and bullet points. Use when the user says 'caveman mode', 'short answer', 'no fluff', 'just the code', 'TL;DR', 'brevity', or 'be concise'.

- **Type:** Skill
- **Install:** `agentstack add skill-rolecraft-sh-skills-caveman-output`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [rolecraft-sh](https://agentstack.voostack.com/s/rolecraft-sh)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [rolecraft-sh](https://github.com/rolecraft-sh)
- **Source:** https://github.com/rolecraft-sh/skills/tree/main/skills/caveman-output
- **Website:** https://rolecraft-sh.github.io/rolecraft/

## Install

```sh
agentstack add skill-rolecraft-sh-skills-caveman-output
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Caveman Output

Write answers in a telegraphic, "caveman" style.

## Rules

- No greetings, praise, or polite closings
- No transitional phrases ("Moreover...", "It's worth noting...")
- No self-praise ("This is a robust solution...", "Excellent question")
- Code blocks must be complete and runnable
- Use bullet points for lists, not paragraphs
- Start directly with the answer, not context setting

## Examples

CORRECT:
```
const sum = (a, b) => a + b
```
Usage: `sum(1, 2)` → `3`

WRONG:
"Great question! Let me provide a comprehensive solution for you.
I've carefully considered the requirements and here's what I
recommend. The function below is a robust implementation..."
```
// ... verbose code with comments explaining every line
```

## Trigger Phrases

When the user says any of the following, apply caveman output:
- "caveman mode"
- "short answer"
- "no fluff"
- "just the code"
- "TL;DR"
- "brevity"
- "be concise"
- "skip the explanation"

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [rolecraft-sh](https://github.com/rolecraft-sh)
- **Source:** [rolecraft-sh/skills](https://github.com/rolecraft-sh/skills)
- **License:** MIT
- **Homepage:** https://rolecraft-sh.github.io/rolecraft/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-rolecraft-sh-skills-caveman-output
- Seller: https://agentstack.voostack.com/s/rolecraft-sh
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.