Ask
- 42 installs
- 52 repo stars
- Updated July 6, 2026
- buiducnhat/cobrew
Ask is a Claude Code skill that gathers missing requirements through focused one-question-at-a-time dialogue before a task is planned or built.
About
Ask is a Claude Code skill for structured requirements gathering through focused dialogue. A developer invokes it when a task is ambiguous or underspecified and user input is needed before any action. It identifies information gaps across objective, scope, constraints, and success criteria, then asks one question at a time without writing code or plans.
- Asks exactly one targeted question per message, preferring 2-4 multiple-choice options
- Strictly ask-only: writes no code and produces no plans or artifacts
- Loads relevant project docs first to avoid re-asking documented answers
Ask by the numbers
- 42 all-time installs (skills.sh)
- Ranked #1,711 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
ask capabilities & compatibility
- Capabilities
- brainstorm · quick implement · write plan
- Use cases
- planning
- Pricing
- Free
What ask says it does
Structured clarification and requirements gathering through focused dialogue or with dry code.
Ask **exactly one question per message**
Apply YAGNI: only ask what is strictly necessary to proceed
npx skills add https://github.com/buiducnhat/cobrew --skill askAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 42 |
|---|---|
| repo stars | ★ 52 |
| Last updated | July 6, 2026 |
| Repository | buiducnhat/cobrew ↗ |
What it does
Clarify an ambiguous or underspecified task by asking one focused question at a time before any planning or coding starts.
Who is it for?
Front-loading clarification on vague or underspecified tasks before work begins.
Skip if: Planning, designing, or implementing anything (it explicitly refuses to write code or artifacts).
When should I use this skill?
A task is ambiguous, underspecified, or requires user input before any action can be taken.
What you get
A closed set of clarifying answers covering objective, scope, constraints, and success criteria.
- A set of answered clarifying questions covering scope and constraints
By the numbers
- Asks one question per message with 2-4 multiple-choice options
Files
Ask
Workflow
Step 1: Gather Project Context
Load only the project context relevant to the current task:
- If
docs/SUMMARY.mdexists, read it first. - Load only task-relevant detail docs.
- Prioritize
Code Standarddocs for implementation conventions. - If docs conflict with code or user intent, use the available input/question before broad changes.
Skip this step if no project docs or useful repository files exist.
Step 2: Identify Information Gaps
Determine exactly what is missing before a task can proceed:
- Objective and user value
- Scope boundaries and non-goals
- Constraints (technical, UX, performance, timeline)
- Success criteria
- Key decisions with multiple valid options
Step 3: Ask Questions (One at a Time)
Ask targeted questions sequentially to close each gap.
Rules:
- Ask exactly one question per message
- Prefer multiple-choice options when practical (2–4 choices)
- Use open-ended questions only when no reasonable options exist
- Do not ask questions already answered by project documentation
- Do not ask about implementation details prematurely
- Do not bundle multiple questions into one message
Rules
- Do not write code or modify any files, only support dry coding into output, not into artifacts
- Do not produce plans, designs, or implementation artifacts
- Do not make assumptions; ask instead
- Keep questions short and focused
- Apply YAGNI: only ask what is strictly necessary to proceed
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493k