Skip to content
Back to skills

Grilling

ASecurity

Use when the user explicitly requests a grilling interview to resolve or challenge material decisions. For a written critique, review the artifact directly.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 15, 2026
securitydocumentation

Security analysis

A100/100

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

Scanned October 15, 2026

npx -y skills add MVPavan/via --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/mvpavan-grilling/badge)](https://www.skillsdirectory.com/skills/mvpavan-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: Use when the user explicitly requests a grilling interview to resolve or challenge material decisions. For a written critique, review the artifact directly.
---

# Grilling

Interview the user about a plan, decision or idea when they explicitly request
that interaction. A request for written critique does not itself request an interview.

Map material decisions and their prerequisites. Ask a manageable batch of
independent questions whose prerequisites are settled; defer dependent questions
until their answers can use the earlier decisions. Include a recommendation and
its assumptions where useful, allowing the user to disagree.

Look up available facts yourself. Ordinary local or documentation lookups stay
inline; delegate only bounded work that benefits from it. Decisions requiring a
live participant remain pending; do not answer on that participant's behalf.

Recompute the unresolved choices after each answer. Stop when the decisions
needed for the requested outcome are settled, explicitly deferred or identified
as blocked. Do not exhaust every imaginable branch. Summarize material agreements
and remaining uncertainty; carry authorization forward for any next step already
requested, without treating the interview itself as implementation authority.

If the necessary respondent is absent, prepare a questionnaire for their role and
knowledge gap. Ask the present user only for missing recipient context and desired
outcome; do not force two exchanges when these were supplied. Drafting a
questionnaire does not authorize sending it.

Documentation is optional. When requested, use domain-modeling for settled terms
and qualifying ADRs; a repository's existence alone does not authorize these writes.

Files in this skill

  • SKILL.md1.7 KB
  • agents/openai.yaml155 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.