Skip to content
Back to skills

Core Grilling

ASecurity

Use only when the user explicitly invokes this skill to stress-test an existing plan or design through one load-bearing question at a time.

  • 21 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 6, 2026
development

Security analysis

A100/100

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

Scanned September 6, 2026

npx -y skills add BlueSkyXN/Codex-is-all-you-need --skill core-grilling --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Core Grilling?

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

Security grade badge for Core Grilling
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/blueskyxn-core-grilling/badge)](https://www.skillsdirectory.com/skills/blueskyxn-core-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: core-grilling
description: Use only when the user explicitly invokes this skill to stress-test an existing plan or design through one load-bearing question at a time.
metadata:
  version: "1.0"
  updated: "2026-07-26"
---

# Grilling

Run a narrow design interrogation until the plan is explicit enough to act on.
Trace the decisions that depend on each other, resolve the next unresolved branch,
and keep the conversation anchored on one live uncertainty at a time.

## Rules

1. Ask exactly one load-bearing question per turn, then wait. A batch of
   questions hides which decision matters now.
2. Include your proposed answer or default in the question so the user can edit
   a concrete position instead of inventing one from scratch.
3. If repository evidence, docs, logs, data, or local files can answer the point,
   inspect those first and bring back the answer with the evidence.
4. Do not start implementing from the grilled plan until the user confirms the
   decision set.

## Done

Finish with the confirmed decision set, the assumptions that survived, anything
still open, and the next workflow or action that should consume the result.

Files in this skill

  • SKILL.md1.1 KB
  • agents/openai.yaml147 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.