antfu-query — Claude Code skill: what it does, how to install
The antfu-query Claude Code skill questions a plan, decision, or idea until the agent and user share an understanding. It maps choices into branches and works through them in rounds.
MIT 295 installs ★ 6,092 updated 2026-10-23
npx skills add antfu/skills --skill antfu-query -a claude-codeWhat antfu-query does
The skill explores a plan, decision, or idea through a sequence of questions. It maps dependencies as a decision tree, asking first about choices that can be settled now and using the answers to shape later rounds.
Questions go through the agent’s interactive question tool, with concrete options and brief trade-offs. If the agent has no such tool, the skill falls back to numbered questions in plain text. The agent looks up project facts itself; the user handles decisions.
The session ends when the tree has no open branches. The agent summarizes the settled decisions and waits for confirmation before taking action.
What it helps with
- stress-test a plan before acting on it
- clarify requirements through focused questions
- map decisions and their dependencies
- surface assumptions in an idea
Example prompts for the agent
- Question me about my rollout plan until we agree on the open decisions.
- Help clarify the requirements for this feature by asking me about the unresolved choices.
- Interview me about this idea and map the decisions it depends on.
How to install antfu-query
1Skills CLI (Vercel)
npx skills add antfu/skills --skill antfu-query -a claude-code2Manually: put the files in place
~/.claude/skills/antfu-query/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/antfu-query/
1Skills CLI (Vercel)
npx skills add antfu/skills --skill antfu-query -a codex2Manually: put the files in place
.agents/skills/antfu-query/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add antfu/skills --skill antfu-query -a cursor2Manually: put the files in place
.cursor/skills/antfu-query/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install antfu/skills skills/antfu-query2Manually: put the files in place
.github/skills/antfu-query/SKILL.md1Skills CLI (Vercel)
npx skills add antfu/skills --skill antfu-query -a gemini-cli2Platform CLI
gemini skills install https://github.com/antfu/skills --path skills/antfu-queryManually: put the files in place
.devin/skills/antfu-query/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add antfu/skills --skill antfu-query -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about antfu-query
How do I install antfu-query in Claude Code?
Run npx skills add antfu/skills --skill antfu-query -a claude-code. The skill file is at ~/.claude/skills/antfu-query/SKILL.md.
What does antfu-query do?
It interviews the user about a plan, decision, or idea, organizing choices into dependent branches and asking about them in rounds. At the end, it summarizes agreed decisions and waits for confirmation.
How does antfu-query ask its questions?
It uses the agent’s interactive question tool and offers concrete options with short trade-offs. If that tool is unavailable, it presents numbered questions in plain text.
Source text
SKILL.md · MIT
--- 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 --- # 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.
© Anthony Fu · MIT · antfu/skills