what-to-ask

GitHub

在签署、购买或达成协议前,针对具体场景生成五个高杠杆问题,附带原因及糟糕回答示例。支持路由至专业解码器,帮助用户识别风险并获取关键书面确认。

exports/openclaw/what-to-ask/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

即将签署合同或协议 准备购买大额商品或服务 询问签约前应问的关键问题 需要识别潜在风险陷阱

Install

npx skills add mohitagw15856/pm-claude-skills --skill what-to-ask -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/what-to-ask -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@what-to-ask

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill what-to-ask -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "what-to-ask",
    "homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/what-to-ask.html",
    "metadata": {
        "openclaw": {
            "emoji": "🧠"
        }
    },
    "description": "Get the five questions that matter before you sign, buy, or agree to anything — the front door to the decoder family, routed by situation. Use when asked what should I ask before signing this, I'm about to buy X what do I check, what questions for the landlord\/dealer\/contractor\/HR, or what am I forgetting. Produces the five highest-leverage questions for the specific situation with why each matters and what a bad answer sounds like, plus the pointer to the full decoder when one exists."
}

What To Ask Skill

Every consequential signature has five questions that would have changed everything — asked the day before instead of discovered the year after. This skill is the library's front door: name the situation ("signing a lease," "buying a used car," "joining a startup," "hiring a contractor"), get the five questions that carry the most leverage for that situation, each with why it matters and what a bad answer sounds like. When a full decoder exists for the document, this skill hands off to it; when none does, five good questions still beat walking in empty.

What This Skill Produces

  • The five questions — highest-leverage first, phrased ready to say out loud
  • Per question: why it matters (the failure it prevents) and what a bad answer sounds like (the tell to listen for)
  • The get-it-in-writing flags — which answers must survive on paper
  • The handoff — the full decoder/calculator/simulator for this situation, when the library has one

Required Inputs

Ask for these if not provided:

  • The situation — what's being signed/bought/agreed, with whom, and when (tomorrow changes the advice from "research" to "triage")
  • The stakes and the worry — money involved, and the thing they're privately nervous about (the fifth question is usually theirs)
  • What's already known — documents in hand get routed to their decoder; verbal-only situations get the questions that force things onto paper

Framework: The Question-Selection Rules

  1. Leverage order, not checklist order: the five are chosen by expected-cost-prevented, not thoroughness — the question that voids the deal outranks ten that adjust it. A list of twenty is a list of zero; five is the format because it forces the ranking.
  2. Every question gets its bad-answer tell: "What happens if I need to exit early?" matters less than knowing that "oh, we're flexible, we'll work with you" is the bad answer — vagueness where numbers should be is the universal tell, and each question names its specific version.
  3. The writing question is always in the five for anything with money attached: some form of "can I get that in writing?" — because the answers to questions 1–4 are worth exactly what they're written on.
  4. Route to depth when it exists: lease → lease-decoder; job offer → benefits-decoder; contractor → home-contractor-quote-decoder; car lot → the-car-dealership to rehearse it first. The five questions are the door; the decoder is the room.
  5. Unknown situations still get real questions — derived from the universal five axes: exit costs (how do I leave?), change costs (what can they change on me?), the money's full shape (what's the all-in number?), failure modes (what happens when something goes wrong?), and verification (how do I check what you just told me?). Any situation on earth maps onto those.

Output Format

Before you [sign/buy/agree]: [situation]

The Five

1. "[The question, verbatim]" Why: [the failure it prevents] · Bad answer sounds like: "[the tell]" · [📝 get in writing]

[…2–5, same shape…]

If You Only Ask One

[Which, and why it carries the most weight here]

Go Deeper

[The library's full treatment for this situation, linked — or "no decoder yet; the five axes above are the map"]

Quality Checks

  • Exactly five questions, leverage-ranked — not a padded checklist
  • Every question has a bad-answer tell, specific to it
  • The in-writing flag appears wherever money does
  • The user's stated private worry became one of the five
  • The handoff link appears when the library covers the situation

Anti-Patterns

  • Do not exceed five — the ranking discipline is the product; a sixth question weakens the first
  • Do not ask questions the user can't act on — every answer must change something
  • Do not phrase questions adversarially — the counterpart is a person; the tells do the detecting
  • Do not skip the handoff to save face — five questions are the trailer, not the movie
  • Do not generate generic questions for a specific situation — "what are the terms?" is what this skill exists to replace

Version History

  • 54fad50 Current 2026-07-19 12:38

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md
exports/openclaw/boolean-search-builder/SKILL.md
exports/openclaw/brag-doc/SKILL.md
exports/openclaw/brainstorming/SKILL.md
exports/openclaw/brief-builder/SKILL.md
exports/openclaw/briefing-note/SKILL.md
exports/openclaw/budget-builder/SKILL.md
exports/openclaw/budget-variance-analysis/SKILL.md
exports/openclaw/bug-diagnosis/SKILL.md
exports/openclaw/bug-report/SKILL.md

Metadata

Files
0
Version
471c606
Hash
115d7cc1
Indexed
2026-07-19 12:38

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-30 11:13
浙ICP备14020137号-1 $방문자$