Ask
- 240 installs
- 52 repo stars
- Updated July 6, 2026
- buiducnhat/agent-skills
ask is a Claude Code skill that runs structured clarification dialogues to gather requirements and project context before any code changes when developer tasks are ambiguous or underspecified.
About
ask is a MIT-licensed Claude Code skill for structured clarification and requirements gathering through focused dialogue. The skill loads only task-relevant project context—prioritizing docs/SUMMARY.md, Code Standard docs, and detail files—then asks targeted questions until scope, conventions, and user intent are explicit. Developers invoke ask when a ticket lacks acceptance criteria, conflicting docs appear in the repo, or an agent might otherwise guess implementation details. The workflow deliberately blocks planning and coding: Step 1 gathers project context, then the agent questions the user until inputs are sufficient. argument-hint supports passing an initial question. Reach for ask at the start of ambiguous refactors, integrations, or feature requests where wrong assumptions would waste diffs.
- Read-only exploration mode
- Blocks unintended file mutations
- Supports architecture Q&A
- Safer pre-implementation discovery
- Complements write-capable agent skills
Ask by the numbers
- 240 all-time installs (skills.sh)
- Ranked #2,629 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/buiducnhat/agent-skills --skill askAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 240 |
|---|---|
| repo stars | ★ 52 |
| Last updated | July 6, 2026 |
| Repository | buiducnhat/agent-skills ↗ |
How do you clarify ambiguous requirements before coding?
Run read-only Claude Code sessions that explore repos, explain code, and answer architecture questions without creating diffs or accidental edits.
Who is it for?
Engineers starting underspecified tickets who want the agent to question assumptions instead of generating premature plans or diffs.
Skip if: Fully specified bug fixes with clear reproduction steps where immediate implementation is appropriate without a clarification pass.
When should I use this skill?
The task is ambiguous, docs conflict with user intent, or the user has not provided enough detail for safe implementation.
What you get
Captured requirements answers, resolved doc conflicts, and explicit scope boundaries ready for a follow-up implementation skill.
- clarified requirements
- scope boundaries
- resolved convention notes
By the numbers
- Workflow Step 1 loads docs/SUMMARY.md and Code Standard docs before questioning
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
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
Does the ask skill write code or plans?
ask does not plan or implement anything. The skill only asks questions and loads task-relevant docs like docs/SUMMARY.md until requirements are clear enough for a separate implementation step.
Which project files does ask read first?
ask prioritizes docs/SUMMARY.md, task-relevant detail docs, and Code Standard documentation. When docs conflict with user intent, ask surfaces the mismatch through targeted clarification questions.