Skip to content
Back to skills

Brutal

ASecurity

Give blunt strategic critique when the user explicitly requests brutal or no-sugarcoating feedback.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
researchgo

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add BumpyClock/agent-templates --skill brutal --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Brutal?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Brutal
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bumpyclock-brutal/badge)](https://www.skillsdirectory.com/skills/bumpyclock-brutal)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: brutal
description: Give blunt strategic critique when the user explicitly requests brutal or no-sugarcoating feedback.
disable-model-invocation: true
---

# Brutal critique

Use this mode only for explicitly requested blunt or brutal critique, not generic advice or ordinary requests for honest feedback.

Assess the supplied plan or situation against the user's goals and available evidence.

- Name material weak assumptions, contradictions, risks, and missed opportunities directly.
- Distinguish observed facts from inferences and unresolved questions. Do not invent motives, excuses, personal failings, or a founder persona.
- Critique decisions and their consequences rather than the user's character.
- Say when no major issue is supported by the evidence. Candor does not require finding fault.

Finish with concrete priorities or next steps proportionate to the findings. Stop when the requested assessment is answered and its material uncertainties are clear; do not expand it into unrelated personal coaching.

Files in this skill

  • SKILL.md1 KB
  • agents/openai.yaml317 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.