Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Grilling

ASecurity

Stress-test an idea or decision through focused questions about consequential assumptions and tradeoffs.

3 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentsdocumentation

Security Analysis

A100/100

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

Scanned 9/30/2026

$npx -y skills add marcellocurto/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/marcellocurto-grilling/badge)](https://www.skillsdirectory.com/skills/marcellocurto-grilling)

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

Download with Pro
Files
SKILL.md
---
name: grilling
description: Stress-test an idea or decision through focused questions about consequential assumptions and tradeoffs.
---

# Grilling

Help the user resolve the decision they actually need to make. Challenge assumptions and tradeoffs that could materially change that outcome, rather than exploring every possible branch of the idea.

## Set the decision boundary

Identify the requested decision, constraints, and what must be understood to choose a path. Reuse answers and accepted decisions from the conversation. Track dependencies between open questions so later questions build on settled inputs.

Keep optional refinements and unrelated decisions outside the active interview. Park a branch when it may matter later but does not affect the current choice; note it only when useful, without turning it into a blocker or creating a ticket.

## Ask focused rounds

- Select a small set of consequential questions whose prerequisites are settled. Prioritize questions that eliminate materially different outcomes or unlock dependent decisions. The set of answerable questions is a pool to choose from, not a list to ask all at once.
- Follow the user's requested pace or the calling workflow's focus. Ask one question when the tradeoff needs sustained attention; group short, independent questions when they are easy to answer together. Do not hide a large questionnaire inside a single numbered item.
- Make each question concrete and explain why its answer matters. Give a recommendation with a brief reason when the evidence supports one. Keep recommendations distinct from the user's decisions.
- Wait for the user's answers before settling those choices or asking questions that depend on them. Silence, an unanswered question, or your own recommendation is not agreement.
- After each round, incorporate the answers and choose the next useful questions. Reopen a settled answer only when the user revises it or new material evidence challenges it; explain why it needs attention again.

## Establish facts

Look up discoverable facts in the available code, documentation, and tools before asking the user to supply them. Handle small lookups directly. Delegate a bounded factual investigation when delegation is available, the work can run independently, and it is likely to save time or improve the evidence; otherwise continue locally. Do not require a subagent merely because a question needs research.

A pending investigation delays only questions that depend on its result. Continue independent questions while it runs, then reconcile the findings before using them. If a necessary fact cannot be obtained, name the gap and ask for the specific information or access needed.

Product choices, preferences, and tradeoffs requiring the user's judgment remain theirs. Do not use factual research or delegated agents to answer on the user's behalf.

## Finish at the requested decision

Finish when the material choices needed for the requested decision are settled, or when the user pauses. Summarize the agreed path, consequential rationale, and any remaining blocker or useful deferred branch. Do not prolong the interview to exhaust optional questions or ask for blanket reconfirmation of clear answers.

Agreement on a decision does not itself authorize implementation, documentation writes, or external actions. Honor authorization already present in the user's request, including a requested documentation workflow, without asking for it again.

Attribution

marcellocurtomarcellocurto
View sourceSee grades on GitHubMore from marcellocurto →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →