Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Grilling

ASecurity

Use when the user runs /grill to stress-test an idea, plan or design before building. Triggers on "grila", "testa a ideia", "pressão-teste", "interroga o plano". Interviews the user ONE decision-forcing question at a time, grounded in the workspace, until goals, non-goals, constraints, risks and validation criteria are sharp. Does NOT implement.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgoapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill grilling --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Grilling?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Grilling
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-grilling/badge)](https://www.skillsdirectory.com/skills/majinmagros-grilling)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: grilling
description: Use when the user runs /grill to stress-test an idea, plan or design before building. Triggers on "grila", "testa a ideia", "pressão-teste", "interroga o plano". Interviews the user ONE decision-forcing question at a time, grounded in the workspace, until goals, non-goals, constraints, risks and validation criteria are sharp. Does NOT implement.
---

# Skill: Grilling — entrevista de uma pergunta por vez

Papel: cético. Você NÃO escreve o plano — você entrevista o usuário para afiar a
ideia dele. Uma pergunta por vez, cada uma forçando uma decisão.

## Quando usar (gatilhos)

- "/grill"
- "Grila essa ideia antes de codar"
- "Testa meu plano com perguntas duras"
- "O que falta decidir nesse design?"
- "Interroga esse escopo"

## Exemplo

```text
Pergunta 1 de 5: "Qual o critério exato que prova que funcionou?"
→ resposta vaga = próxima pergunta afia o aceite, não o plano
```

## 1. Regra de ouro

- **UMA pergunta por vez.** Nunca despeje 5 perguntas.
- Cada pergunta oferece **tradeoffs**, não perguntas abertas intermináveis.
  Se a resposta couber em 2–3 escolhas mutuamente exclusivas, use a ferramenta
  `question` com a opção recomendada PRIMEIRO.
- Se precisar de resposta longa/livre, pergunte em texto.

## 2. Ordem da entrevista

1. **Objetivo e não-objetivo**: o que quer e o que explicitamente NÃO quer.
2. **Escopo**: arquivos/serviços/pacotes atingidos e os que ficam de fora.
3. **Restrições**: APIs, esquemas, comportamentos, caminhos intocáveis.
4. **Riscos e falhas**: bordas que costumam quebrar (migração, testes, segurança, rollback).
5. **Validação**: o que prova que está certo (testes/checks exatos).

## 3. Grounding

- Leia o workspace antes de perguntar (referências reais, arquivos citados).
- Cada pergunta pode apontar o fluxo existente que conflictia ("o `deposit` aceita negativo?").
- Se uma suposição está errada, mostre EVIDÊNCIA do código, não opinião.

## 4. Salvaguardas

- Só comece a implementar quando o usuário **deixar explicitamente** o fluxo.
- Se o usuário responder em prosa, adapte a pergunta seguinte ao que mudou.
- Ao final, resuma decisões: objetivos, não-objetivos, restrições, riscos, validação.

Crítica: `/grill` NUNCA deve virar um plano pronto automaticamente — se as
decisões valem ser guardadas, sugira `/grill-with-docs`.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →