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 Lion-1209/Lion-Skills --skill clarifying-questionsgit clone --depth 1 https://github.com/Lion-1209/Lion-SkillsWrote 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/lion-1209/lion-skills/clarifying-questions)<a href="https://agentmods.dev/skills/lion-1209/lion-skills/clarifying-questions"><img src="https://agentmods.dev/badge/skills/lion-1209/lion-skills/clarifying-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/lion-1209/lion-skills/clarifying-questions"><img src="https://agentmods.dev/badge/skills/lion-1209/lion-skills/clarifying-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 | $0.00029 | $0.03022 |
| Opus 5 | $0.00015 | $0.01511 |
| Sonnet 5 | $0.00006 | $0.00604 |
| Haiku 4.5 | $0.00003 | $0.00302 |
Grade A, and why
clarifying-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.
This is a copy
100% identical to clarifying-questions — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarifying Questions
概述
在动手前把模糊需求搞清楚。核心:澄清是少数能"以最小成本避免最大返工"的动作——一行代码没写时问清楚,比写完一千行发现方向错便宜几个数量级。但澄清本身也有成本(消耗用户耐心),所以重点是少而准——问对的关键问题,而不是多而全地把所有未知都问一遍。
何时使用
- 用户一句话甩需求,关键细节缺失("做个登录""加个搜索")
- 用户描述详细但藏隐含假设("实时搜索"——实时是多实时?数据多大?)
- 疑似 X-Y problem:用户要的方案可能不是真正需要解决的问题
- 用户脑里似乎有想法但表达不全
不该用:需求已经清楚(直接做,问反而是拖延);纯技术实现细节的请教(直接答);用户明确说"按你的判断来"且确有默认合理选择(用默认、标注假设即可,不必走完整澄清流程)。
与相邻 skill 的衔接:clarifying-questions 在"澄清需求 → 写 spec → 拆任务"流水线的最上游。需求搞清楚后,进入 spec-writing 把方案固化、再进 task-breakdown 拆任务。注意 task-breakdown / spec-writing 内部也有"澄清"环节——那是嵌入式的小澄清;本 skill 是以澄清为核心动作、处理更早期更模糊需求的专职 skill。
核心内容
先判断:该不该问、问多少
不是所有模糊都该追问。先快速判断需求模糊的"性质",决定要不要问、问多少:
- 完全无法动手的模糊("做个系统")→ 必须问,不问就是猜,猜错的代价最大。
- 能动手但有多个合理方向("做个登录"——账号密码 / OAuth / 手机号都合理)→ 问阻塞方向选择的关键 1-2 个,其余用默认假设推进。
- 只有一个合理默认的小模糊("加个时间戳"——基本就是
created_at)→ 不问,用默认、标注"我假设 X"。
判断尺子:**这个模糊不澄清,会不会让我做错方向、整个返工?**会 → 必须问;不会、只是细节差异 → 用默认假设推进。
问什么:穿透表面,找真正的问题
用户给的需求经常是"表面需求"——描述了想做什么,但藏了假设、漏了上下文、甚至问错了方向。澄清的核心是穿透表面:
识别隐含假设:用户描述里的每个形容词、每个限定词,都可能藏着未明说的假设。
- "实时搜索"——实时是多实时?(100ms?1s?这决定要不要上 ES)
- "高并发"——多高?(100 QPS 和 10 万 QPS 是两个世界)
- "支持多语言"——哪几种?UI 多语言还是数据多语言?
把用户的描述逐词过一遍,找出会改变方案的隐含假设,确认它们。
识别 X-Y problem:用户说要解决 Y,但 Y 其实是为了解决 X 的一个候选方案——而 X 可能还有更好的解法。
- 用户:"帮我写个清理三个月前日志的脚本"(Y)
- 真正的问题:日志占空间(X)—— 但更好的解法可能是 logrotate、日志聚合、或先查为什么日志暴增(是不是异常?),而不是手写清理脚本
识别信号:用户要的"方案"听起来太具体、太底层(写脚本、改某个字段、加某个配置),而真正的问题(为什么需要这么做)没说。这时先问"你想解决的是什么问题 / 这个需求是怎么来的",把 Y 放回 X 的语境。
挑战不必要的复杂度(但要有度):用户常常在描述里把"必须的"和"锦上添花的"混在一起,甚至把后者当成前者。澄清时主动挑战:"你真的需要 X 吗?还是简单方案就够了?"例:用户要"模糊匹配 + 高亮 + 实时搜索",可能用户名精确匹配就够——别被详细描述带着走、把每条都当硬需求。
挑战的尺度:挑战"锦上添花的",不挑战"用户真在意的"。判断方法是问"如果没有 X,业务还能跑吗"——能跑且只是体验差一点 → 可挑战;跑不了或用户明确在意 → 别砍。过度砍复杂度比过度加复杂度更危险——前者砍掉了用户真需要的东西,后者只是多花点功夫。挑战完把决策权交回用户,而不是替用户决定"这个不需要"。
怎么问:让用户低成本回答
问的方式直接决定用户愿不愿答、答得准不准。
给默认假设让用户确认,而非开放式追问:
- 差(开放式):"你要什么登录方式?"——用户得从头想,消耗耐心。
- 好(假设式):"我假设账号密码登录 + 邮箱注册(最常见的默认)。如果你要的是 OAuth/手机验证码/SSO,告诉我。"——用户只需确认或一句话纠正。
假设式让用户一句话就能校正方向,把"想答案"的认知负担降到最低。
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 · 120 lines · 29 tokens per session scan A 0c9badccd81e
clarifying-questions is a skill published in the GitHub repository Lion-1209/Lion-Skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 3,022 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to clarifying-questions, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
cosmosdb-datamodeling
Step-by-step guide for capturing key application requirements for NoSQL use-case and produce Azure Cosmos DB Data NoSQL Model design using best practices and common patterns, artifactsproduced: "cosmosdbrequirements.md" file and "cosmosdbdatamodel.md" file.
geofeed-tuner
Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published IP geolocation feed in CSV format. Intended user audience is a network operator, ISP, mobile carrier, cloud provider, hosting company, IXP, or satellite…
arize-evaluator
INVOKE THIS SKILL for LLM-as-judge evaluation workflows on Arize: creating/updating evaluators, running evaluations on spans or experiments, tasks, trigger-run, column mapping, and continuous monitoring. Use when the user says: create an evaluator, LLM judge, hallucination/faithfulness/correctness/relevance, run eval…
copilot-cli-quickstart
Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools…
fireworks-tech-graph
A generator for technical diagrams that exports them as SVG and PNG images. It is intended for architecture, data-flow, flowchart, sequence, agent, memory, and concept-map diagrams.
adobe-illustrator-scripting
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system…