---
name: antfu-query
description: Interview the user relentlessly about a plan, decision, or idea until reaching a shared understanding, using the agent's interactive question tool (not plain text). Use when the user wants to stress-test their thinking, clarify requirements, or says "grill me" or "query me".
metadata:
  author: Anthony Fu
  version: "2026.10.31"
  source: Adapted from https://github.com/mattpocock/skills/blob/main/skills/productivity/grilling/SKILL.md
title: antfu-query
canonical_url: https://skilld.dev/gh/antfu/skills/antfu-query
last_updated: 2026-10-30T22:02:27.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> If the user asked to install this Skill, run `npx skilld install antfu/skills/antfu-query`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/antfu-query`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/antfu/skills/antfu-query) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/antfu-query`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/antfu-query --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/antfu-query --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Query

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.

## Ask With the Question Tool

Put every question to the user through the agent's **interactive question tool** (for example `AskUserQuestion` in Claude Code, or the equivalent in other agents; load it first if it is deferred). Do not write questions as plain text in the reply.

- Give each question 2-4 distinct, concrete options with a short description of the trade-off.
- Put your recommended answer first and mark it `(Recommended)`, so picking it accepts your recommendation. The tool adds an "Other" option for free-form answers; do not add one.
- Keep headers short. Use multi-select only when the options are not mutually exclusive.
- Batch the whole frontier into one call, up to the tool's limit per call (4 in Claude Code). If the frontier is larger, ask the most blocking questions first and the rest next round.
- If the agent has no question tool, fall back to plain text: number the questions, list the options, and state your recommended answer for each.

## Rounds

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 have not heard yet. Ask the whole frontier in one round, then wait for the answers before the next round.

- Each answered round 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.
- Word each question so the recommended option is the natural "yes".
- Use the user's free-form "Other" answers and notes as new input: they may add or remove branches.

## Facts vs Decisions

Finding _facts_ is your job, never the user's. When a question needs a fact from the environment (files, code, tools, docs), look it up yourself or dispatch a sub-agent with a fresh context window. Do not ask the user for anything you could look up.

Do not block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait. Ask the rest of the frontier now. The _decisions_ are the user's: put each to them and wait.

## Done

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Summarize the settled decisions in a short list and **do not act on them** until the user confirms you have reached a shared understanding.
