Use This Skillgrilling
ProvenGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
No fetch-and-execute, destructive, credential, exfiltration or rules-override patterns in 2 files, checked on Oct 24, 2026. This is not a guarantee of safety. How the scan works.
Author? Show the scan result in your README
The badge updates with each weekly scan.
npx degit mattpocock/skills/skills/productivity/grilling .claude/skills/grillingWith and without this skill.
Prompt: “Here is my plan. I want to launch a paid newsletter for independent game developers in six weeks. It will cost $8 a month, come out every Tuesday, and cover marketing tips, funding opportunities and interviews with developers who shipped on Steam. I have 1,200 followers on X and no email list yet. My goal is 500 paying subscribers in the first year. Grill me on this plan, and present the result as a single HTML page: every question you would ask me, in the order you would ask it, why each one matters, and what a weak answer would tell you.” Run on claude-opus-5-5, with the skill at commit 5beb35b. Recorded 10/24/2026. 3 independent runs per side; all are shown, none picked by hand.
| Median per run | Without | With the skill | Change |
|---|---|---|---|
| Tokens in (prompt and skill) | 374 | 1,057 | +183% |
| Tokens out | 27,322 | 23,086 | -16% |
| Seconds | 241.8 | 215.7 | -11% |
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. Format a round like so: ``` ❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices> ➡️ <your recommended answer> --- ❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices> ➡️ <your recommended answer> ``` Word each question so "yes" accepts 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. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The _decisions_ are the user's: put each to them and wait. 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.
Shown under the source repo’s MIT license. Read the full folder on GitHub.