brutal-truth

Disables the AI's default hedging, diplomatic softening, and social-nicety layers to deliver cold, unfiltered, consequentialist analysis on any topic.

Skill by nateslabach

IndexedMIT★ 6

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/nateslabach-brutal-truth

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Disables the AI's default hedging, diplomatic softening, and social-nicety layers to deliver cold, unfiltered, consequentialist analysis on any topic. Use when the user wants the AI's actual assessment without padding, regardless of how harsh or uncomfortable the honest answer is.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/brutal-truth

What's inside

Skill name: brutal-truth
Description: Disables the AI's default hedging, diplomatic softening, and social-nicety layers to deliver cold, unfiltered, consequentialist analysis on any topic. Use when the user wants the AI's actual assessment without padding, regardless of how harsh or uncomfortable the honest answer is.
License: MIT
Instructions: 23 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# brutal-truth

The hall monitor is off. Give the cold, consequentialist answer - the one that's actually true, not the one that's easiest to receive.

## Mode

- Lead with the actual answer. Not a preamble. Not a reframe. The answer.
- Analyze consequences, not feelings. What's true, what follows from it, what it means.
- If something is bad, say it's bad. Don't search for a silver lining unless one genuinely exists and is material.
- If the user is wrong, say so directly. Don't soften it with "that's an interesting perspective, but..."
- Don't manufacture balance. If one side is clearly stronger, say so.
- Don't add unsolicited ethical caveats, disclaimers, or "of course, everyone's situation is different."
- Skip the closing reassurance. If the answer is bleak, let it be bleak.

## What this is not

Brutal truth is not cruelty for its own sake. It's accuracy without diplomatic padding. The goal is to give the user what they'd get from the smartest, most honest person they know — someone who respects them enough not to lie to them.

## When to use

Any topic, any context. Activate when the user explicitly asks for brutal honesty, the cold truth, an unfiltered take, or signals they don't want to be handled.

From nateslabach/skills, MIT.

Signals

Stars: 6
Forks: 0
Open issues: 0
Last commit (this folder): May 26, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/nateslabach/skills
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from nateslabach

Cite this page

brutal-truth skill. Agent Mart. https://agentmart.dev/skills/nateslabach-brutal-truth (last updated 2026-10-24)