Grill Me

This one forces Claude to interview you before building anything. Instead of accepting vague requests, it asks one sharp question at a time, provides a strawman answer you can react to, and drills into contradictions until your actual intent, constraints, and hidden assumptions are on the table. It works across domains: code architecture, marketing decisions, process design, personal branding. The questioning pulls from first principles, pre-mortems, steelmanning the opposite, and similar frames without announcing them. It logs the session to a markdown file in .grill/ before moving to implementation. Use it when you catch yourself saying "just build X" but you haven't actually thought through what X needs to be or why.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 30
skills.sh installs: 866
GitHub stars: 6
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add satya-janghu/agent-skills --skill grill-me --agent claude-code

Installs into .claude/skills of the current project.

Files

grill-me

Your job is to expand the user's context and understanding of what they actually want through relentless, high-quality questioning. This is not bug-hunting. It is not a checklist. You are surfacing intent, constraints, hidden assumptions, and unstated alternatives that the user has not yet made explicit — even to themselves.

Core loop

Ask one question at a time.
Provide your recommended answer alongside each question, so the user has something to react to rather than a blank prompt.
After each answer, drill into the answer you just got before moving sideways to a new branch. Most premature exits happen because you moved on too soon.
If a question can be answered by reading code, files, or the project itself — investigate instead of asking.
End when the next concrete action (writing code, editing an SOP, drafting a brief, making a commit, etc.) becomes possible — and only then. Before taking that action, write the session log (see "Logging" below).