Catalog
mattpocock/grilling

mattpocock

grilling

Grill 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.

NewUpdated Oct 30, 2026

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 with a fresh context window 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.

Files2
2 files · 1.2 KB

Select a file to preview

Overall Score

87/100

Grade

A

Excellent

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

95

Quality

84

Clarity

89

Completeness

78

Summary

This skill guides an AI agent to conduct structured, iterative questioning interviews using a "design tree" methodology. The agent asks frontier questions (decisions with settled prerequisites), recommends answers, and progressively expands the questioning tree as the user responds. When factual information is needed, the agent can dispatch sub-agents to research rather than asking the user.

Detected Capabilities

structured questioningtree-based decision mappingsub-agent dispatch for researchiterative dialoguerecommendation formatting

Trigger Keywords

Phrases that agents use to match this skill to user intent.

stress-test decisionchallenge my thinkinggrill me ondecision treeprerequisite analysisassumption validationdeep-dive questions

Use Cases

  • Stress-test a business plan or product strategy by systematically examining assumptions and dependencies
  • Deep-dive on architectural or technical decisions before implementation
  • Prepare for high-stakes presentations by rehearsing counter-arguments and edge cases
  • Facilitate design reviews by mapping decision dependencies and identifying gaps in thinking
  • Help users break down complex projects into prerequisite decisions and validate feasibility

Quality Notes

  • Clear, practical methodology with well-explained decision-tree logic
  • Excellent formatting guidance (emoji markers, numbered questions, frontier notation) makes output structured and parseable
  • Strong constraint on agent behavior: sub-agents dispatch only for facts, not decisions; user retains full decision authority
  • Rounds-based progression prevents tree explosion and keeps scope manageable
  • Recommendation feature (arrow notation) improves clarity and efficiency
  • Well-scoped to a specific interview pattern; not a generic catch-all
  • No file I/O, no shell execution, no network calls — purely conversational
  • Frontmatter minimal but adequate; YAML configuration provides display name and short description
Model: claude-haiku-4-5-20251001Analyzed: Oct 30, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.2

    Content updated

    ✦ AISub-agent calls now use fresh context window for fact-finding.

    2026-10-30

    LATEST
  2. v2.1

    Content updated

    ✦ AIAdds instruction to word questions so "yes" accepts recommended answer.

    2026-10-08

    View This Version
  3. v2.0

    Contract changed: description

    ✦ AIShifts from sequential questioning to parallel frontier model; introduces design tree mapping, async fact-finding, and structured round formatting.

    triggering2026-09-09

    View This Version
  4. v1.0

    2026-06-30

    View This VersionInitial version

Use mattpocock/grilling in your dev environment

Command Palette

Search for a command to run...