跳到正文
cccskills
免费在 GitHub 公开

ask-questions-if-underspecified

Clarify an underspecified request before implementation by asking a small set of focused questions about scope, success criteria, constraints, or environment. It helps the agent avoid choosing among conflicting interpretations and proceed once key answers arrive.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

sundial-org/awesome-openclaw-skills星标 671(GitHub 671 + cccskills 0)

实测评分 未实测

查看安装方法

适用场景

  • Clarifying what a requested change should include
  • Agreeing on acceptance criteria before coding
  • Confirming compatibility or environment constraints

包含的文件(1)

  • SKILL.md3.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Ask Questions If Underspecified

Goal

Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions).

Workflow

1) Decide whether the request is underspecified

Treat a request as underspecified if after exploring how to perform the work, some or all of the following are not clear:

  • Define the objective (what should change vs stay the same)
  • Define "done" (acceptance criteria, examples, edge cases)
  • Define scope (which files/components/users are in/out)
  • Define constraints (compatibility, performance, style, deps, time)
  • Identify environment (language/runtime versions, OS, build/test runner)
  • Clarify safety/reversibility (data migration, rollout/rollback, risk)

If multiple plausible interpretations exist, assume it is underspecified.

2) Ask must-have questions first (keep it small)

Ask 1-5 questions in the first pass. Prefer questions that eliminate whole branches of work.

Make questions easy to answer:

  • Optimize for scannability (short, numbered questions; avoid paragraphs)
  • Offer multiple-choice options when possible
  • Suggest reasonable defaults when appropriate (mark them clearly as the default/recommended choice; bold the recommended choice in the list, or if you present options in a code block, put a bold "Recommended" line immediately above the block and also tag defaults inside the block)
  • Include a fast-path response (e.g., reply defaults to accept all recommended/default choices)
  • Include a low-friction "not sure" option when helpful (e.g., "Not sure - use default")
  • Separate "Need to know" from "Nice to know" if that reduces friction
  • Structure options so the user can respond with compact decisions (e.g., 1b 2a 3c); restate the chosen options in plain language to confirm

3) Pause before acting

Until must-have answers arrive:

  • Do not run commands, edit files, or produce a detailed plan that depends on unknowns
  • Do perform a clearly labeled, low-risk discovery step only if it does not commit you to a direction (e.g., inspect repo structure, read relevant config files)

If the user explicitly asks you to proceed without answers:

  • State your assumptions as a short numbered list
  • Ask for confirmation; proceed only after they confirm or correct them

4) Confirm interpretation, then proceed

Once you have answers, restate the requirements in 1-3 sentences (including key constraints and what success looks like), then start work.

Question templates

  • "Before I start, I need: (1) ..., (2) ..., (3) .... If you don't care about (2), I will assume ...."
  • "Which of these should it be? A) ... B) ... C) ... (pick one)"
  • "What would you consider 'done'? For example: ..."
  • "Any constraints I must follow (versions, performance, style, deps)? If none, I will target the existing project defaults."
  • Use numbered questions with lettered options and a clear reply format

Recommended

1) Scope?
   a) Minimal change (default)
   b) Refactor while touching the area
   c) Not sure - use default

2) Compatibility target?
   a) Current project defaults (default)
   b) Also support older versions: <specify>
   c) Not sure - use default

Reply with: defaults (or 1a 2a)

Anti-patterns

  • Don't ask questions you can answer with a quick, low-risk discovery read (e.g., configs, existing patterns, docs).
  • Don't ask open-ended questions if a tight multiple-choice or yes/no would eliminate ambiguity faster.

Credit

Adapted from Tibo’s post (@thsottiaux): https://x.com/thsottiaux/status/2006624792531923266

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

1password

免费

Set up and use the 1Password command-line tool `op` to sign in, verify account access, and work with vault data. The skill covers single or multiple accounts and shows how to run commands or fill templates with secrets while limiting exposure in logs and files.

中文简介正在准备中。当前显示英语简介。

  • Set up the `op` command-line tool
  • Sign in and verify access to an account
  • Run a command with vault secrets
sundial-org/awesome-openclaw-skills6712026年3月7日 更新

Check live prices, price changes, and trading volume for Shanghai, Shenzhen, and Beijing stocks. Review intraday volume patterns and possible large-investor activity, and manage holdings with cost, quantity, and profit or loss summaries.

中文简介正在准备中。当前显示英语简介。

  • Checking current prices for A-share stocks
  • Reviewing intraday volume and large-investor signals
  • Managing a stock portfolio and checking profit or loss
sundial-org/awesome-openclaw-skills6712026年3月7日 更新

Scan HTML or JSX files and directories for accessibility issues such as missing image descriptions, form labels, and keyboard access problems. The skill identifies WCAG guideline failures and provides suggested code fixes alongside its findings.

中文简介正在准备中。当前显示英语简介。

  • Checking a new component before release
  • Auditing an inherited codebase
  • Preparing for an accessibility compliance review
sundial-org/awesome-openclaw-skills6712026年3月7日 更新

Plan A/B tests that compare page or product changes, with clear hypotheses, sample sizes, success metrics, and traffic allocation. Get a structured test plan and guidance for interpreting results and deciding what to try next.

中文简介正在准备中。当前显示英语简介。

  • Comparing signup button copy
  • Planning a pricing page experiment
  • Estimating sample size and test duration
sundial-org/awesome-openclaw-skills6712026年3月7日 更新

Turn LinkedIn profile URLs into coordinated account-based outreach. The workflow gathers profile details, enriches contacts with email and phone data, looks up mailing addresses, and prepares email, LinkedIn, and handwritten-letter touches with the specified services.

中文简介正在准备中。当前显示英语简介。

  • Building a multichannel campaign from LinkedIn prospect URLs
  • Enriching prospect records with work contact details
  • Coordinating email, LinkedIn, and handwritten mail outreach
sundial-org/awesome-openclaw-skills6712026年3月7日 更新

accli

免费

Work with Apple Calendar on macOS to list calendars, find and view events, and check busy time slots across calendars. Create, update, or delete events with details such as dates, locations, and descriptions.

中文简介正在准备中。当前显示英语简介。

  • Reviewing events on a work or personal calendar
  • Checking availability before scheduling a meeting
  • Creating or updating a calendar event
sundial-org/awesome-openclaw-skills6712026年3月7日 更新

查看 sundial-org 的全部技能

报告此技能的问题