A relentless interview to sharpen a plan or design.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add sherifabdlnaby/skills --skill grill-me --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Grill Me?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/sherifabdlnaby-grill-me)More formats (shields.io, HTML) on the badges page.
---
name: grill-me
description: A relentless interview to sharpen a plan or design.
disable-model-invocation: true
---
Call the Skill tool with "grilling".
**Every round goes through the harness's ask-the-user tool, overriding the markdown template `grilling` shows.** Whatever this harness names it: `AskUserQuestion` in Claude Code, `AskQuestion`
(`cursor/ask_question`) in Cursor, `question` in opencode. Each frontier question becomes one question in the call, its candidate answers become the options, and the recommended option goes first,
labelled `(Recommended)`. A frontier wider than the tool's question cap goes out as back-to-back calls, still one round. The user picks; nothing is put to them as prose.
**Every question stays answerable off-list.** Claude Code and opencode already offer free text beside the options, and Claude Code rejects an explicit "Other", so add nothing there. Cursor accepts
only the options it is handed, so give it one that invites a custom answer.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
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.
