Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add WenXuanHe/how-to-ask-questions-skill --skill how-to-ask-questionsgit clone --depth 1 https://github.com/WenXuanHe/how-to-ask-questions-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wenxuanhe/how-to-ask-questions-skill/how-to-ask-questions)<a href="https://agentmods.dev/skills/wenxuanhe/how-to-ask-questions-skill/how-to-ask-questions"><img src="https://agentmods.dev/badge/skills/wenxuanhe/how-to-ask-questions-skill/how-to-ask-questions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wenxuanhe/how-to-ask-questions-skill/how-to-ask-questions"><img src="https://agentmods.dev/badge/skills/wenxuanhe/how-to-ask-questions-skill/how-to-ask-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.03004 |
| Opus 5 | $0.00046 | $0.01502 |
| Sonnet 5 | $0.00018 | $0.00601 |
| Haiku 4.5 | $0.00009 | $0.00300 |
Grade A, and why
how-to-ask-questions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How to Ask Questions — 提问工具箱
高可信元规则：事实 > 看法 · 过去 > 假设 · 追问 > 首答 · 诊断 > 建议 · 清晰 > 花哨
定位：这是主流程版，适合先把问题问准、边界问清、动作压实。
如果目标是压力测试 / 红队审查文章或论点，改用how-to-ask-questions-redteam。
Coverage Note
- 强支持：The Mom Test、The Coaching Habit、Anthropic Prompting Best Practices
- 中等支持：Tim Ferriss 17 Questions、Learner vs Judger、5 Whys、First Principles
- 暂不纳入可教框架：Humble Inquiry、HBR The Surprising Power of Questions、Paul-Elder 8 Elements、Question Bursting
- 原因：当前研究 notebook 对这些内容要么缺原文，要么只有书单、空 PDF、标题或不完整摘要，不应该装作已经掌握
When to Use This Skill
在下面几类场景调用：
| 场景 | 触发信号 | 主工具 |
|---|---|---|
| A. 验证需求 | “这个产品有人要吗？”、“怎么做用户访谈？” | The Mom Test |
| B. 教练式对话 / 卡住破局 | “卡住了”、“不知道怎么继续”、“怎么带人而不是替人做？” | The Coaching Habit + Tim Ferriss |
| C. 根因分析 | “为什么会这样？”、“这个 bug / 事故根因是什么？” | 5 Whys |
| D. 从零重构 | “别人的套路不适用”、“能不能从头拆掉重来？” | First Principles |
| E. 对 AI 提问 | “这个 prompt 怎么写？”、“模型输出总是跑偏” | Anthropic Prompting Best Practices |
边界：
- 纯情绪承接、人生反思、关系安慰，不要硬套这份 skill。
- 需要严密“逻辑审计 / Paul-Elder 8 元素 / HBR 实证 / Question Bursting”时，这个 skill 目前不应假装会。
0. 路由：先判断你在问谁、问什么
你现在是在问谁？
│
├─ 问人
│ ├─ 想验证需求 / 痛点？ → §1 The Mom Test
│ ├─ 想带人思考 / 自己卡住？ → §2 Coaching + Ferriss + Learner
│ ├─ 想追查某次失败的根因？ → §3 5 Whys
│ └─ 想从零重构方案？ → §4 First Principles
│
└─ 问 AI
└─ 想提高输出质量 / 稳定格式？ → §5 LLM Prompting
1. 场景 A：验证需求（The Mom Test）
三条硬规则
- 聊他们的生活，不聊你的想法。
- 问过去的具体行为，不问未来的假设。
- 如果这次对话真的重要，最后要拿到某种承诺。
坏问题 -> 好问题
| 坏问题 | 好问题 | 为什么更好 |
|---|---|---|
| 你觉得这个产品怎么样？ | 请带我走一遍你上次处理这个问题的过程。 | 从评价创意，改成观察现实 |
| 如果有这个功能你会用吗？ | 你现在怎么解决？试过什么？ | 过去行为比未来假设更可靠 |
| 这个价格你觉得贵吗？ | 你现在每月/每年为这个问题花多少时间或钱？ | 事实比主观看法更有价值 |
| 你喜欢这个想法吗？ | 这个问题最近一次让你头疼是什么时候？ | 赞美不是验证 |
访谈四步
Step 1. 锁定一次真实发生：你上次遇到这个问题是什么时候？
Step 2. 还原现有流程：当时你怎么做的？用了什么工具？
Step 3. 测痛点强度：你试过什么替代方案？花过什么代价？
Step 4. 要推进而不是要赞美：你愿不愿意给时间 / 引荐 / 预付 / 数据？
这类场景最容易犯的错
- 把“好主意”“我会用”当验证
- 过早展示 demo，导致对方开始礼貌点评
- 用户提功能就照单全收，不追问背后动机
- 只验证“我能不能做”，不验证“对方到底在不在乎”
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 299 lines · 91 tokens per session scan A 8dcf19b1e616
how-to-ask-questions is a skill published in the GitHub repository WenXuanHe/how-to-ask-questions-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 3,004 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…