Skills for Real Engineers. Straight from my .agents directory.
asking-user-questions
Agent skill fromJetBrains/thinkrail
Use when composing an ask_user_question round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.
How to install asking-user-questions
npx skills add JetBrains/thinkrail# or add only this skill to Claude Code: copy the folder
packages/pi-thinkrail-workflow/skills/asking-user-questions/
# into
~/.claude/skills/asking-user-questions/ (all projects)
.claude/skills/asking-user-questions/ (one project)
1# Asking User Questions23The workflow family's shared norms for `ask_user_question`: how to interview in rounds, what makes a4question worth asking, how to shape options, and how to degrade when answers don't come. Process5skills name this concept at the steps that ask; *when* to ask — and where the answers get recorded —6stays with the referencing skill.78## Interview in rounds until nothing is assumed910- Map the subject as a **design tree**: every decision branches into the decisions that hang off it.11 The **frontier** is every open decision whose prerequisites are already settled — the questions you12 can ask *now* without guessing at answers you haven't heard.13- One call = one **round** = the whole frontier, with no cap on its size. A question whose answer14 depends on another question still open belongs to a *later* round, never the same one. Never split15 independent questions across back-to-back calls.16- **The call blocks the current run.** Answers arrive as this tool's result. Don't keep working on the17 blocked step or assume an answer until it arrives — seconds or days later. A composer message sent18 while the card is open supersedes the round: the card closes unanswered and the message arrives as19 the next user message, so treat it as the user's reply and re-ask only what still matters.20- After each round, recompute the frontier: answers settle branches, unblock their dependents, and21…
Excerpt shown under the repository's Apache-2.0 license.
More skills in thinkrail
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
