Skip to content
Back to skills

Grilling

ASecurity

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, uses any 'grill' trigger phrases, or when a direction owner's rule calls for convergence rounds.

  • 2 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added October 24, 2026
ai-agents

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 24, 2026

npx -y skills add byheaven/byheaven-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 with every re-scan.

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

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: grilling
description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, uses any 'grill' trigger phrases, or when a direction owner's rule calls for convergence rounds.
---

Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.

Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled: the questions you can ask _now_ without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.

When the user's global rules set a format or route for messages that need the user's reply, follow them. Otherwise, format each question like so:

```
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>
```

Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a _later_ round, not this one.

Finding _facts_ is your job, never the user's. Obtain an environmental fact directly when a focused read or observation is sufficient. Delegate bounded investigation when independent work, specialist observation, or context isolation adds enough value to cover its handoff and integration cost; use the host workflow's production-topology rule when one applies. Do not ask the user for a fact you can obtain. A running investigation is an unsettled prerequisite: only its dependent questions wait, while independent work can continue. User-owned decisions still return to the user.

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.

Files in this skill

  • LICENSE1 KB
  • SKILL.md2.1 KB
  • agents/openai.yaml113 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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

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