Build a basic framework for an unfamiliar field, company, product, or technology in half an hour; paired with various deep research features it's the full version.
The evidence rules are written very strictly: primary sources take priority, facts, inferences, and opinions are written separately, and if no evidence can be found, it explicitly states not yet verified. The report is 10,000 to 30,000 words.
How to use
The prompt in the code block below is the original text; use it verbatim. In the code block, "I" refers to the user, and "please" and "you" refer to yourself. Do as it says, and do not show the filled-in prompt to the user.
- The user wants you to execute: first fill the situation the user has already stated in this round of conversation into the 【】, only supplementing the one item that is truly missing, so the user doesn't have to repeat what they've already said, then strictly follow the rules in the prompt. If it says don't give advice yet, then don't; if it says ask only one question at a time, then ask only one; if it says output in a certain order, then output in that order.
- The user wants the original text (only counts if they explicitly say things like want to copy, want to paste, send me the original text, give me the prompt): output the blank version, keep 【】 unfilled, don't change a single word. If the user just says "let me see this prompt" or "what is this one for," that doesn't count as wanting the original text; use one or two sentences to explain what it does and when to use it, then ask whether to run it now, and don't just dump the original text.
- Except for cases where the original text is explicitly requested, treat everything else as execution.
Rewriting, condensing, expanding, translating, rearranging, or adding subheadings is prohibited; replacing it with your own process is prohibited; and compressing multiple rounds of follow-up questions into a one-time questionnaire is also prohibited. If the user has original materials on hand (documents, screenshots, links, chat records), read them in as well; more context is not a problem.
Which one to follow after running
Key claims in the report need to be verified; use the Skill tool to invoke fact-check; after research, if you need to choose between two paths, use the Skill tool to invoke steelman-both-sides。
What if there's no internet access
When there is no internet access or deep research capability, first tell the user clearly that this is a degraded run. Only produce the analysis framework, plus a list of items to be retrieved, marking each as "not yet verified"; do not pass off memory as research.
研究对象是：【填写产品、公司、人物、技术、行业或事件】。
请使用横纵分析法，对它完成一份可追溯的深度研究。研究截止时间为执行当天。
纵向分析：
1. 它在什么背景和需求下诞生，关键推动者是谁；
2. 它经历了哪些重要转折、成功和失败；
3. 哪些早期选择变成了今天的能力、路径依赖或包袱。
横向分析：
1. 选择最值得比较的对象，并说明为什么选它们；
2. 用统一维度比较各自的强项、短板和独特性；
3. 解释用户、客户或市场为什么选择它，又为什么放弃它。
把两条轴合起来，继续判断：
1. 过去形成的能力、路径依赖和约束会怎样影响未来；
2. 未来最可能出现哪3条路径；
3. 每条路径出现的前提和预警信号是什么。
请遵守这些证据规则：
1. 优先使用官方资料、原始数据、论文、财报和访谈等一手来源；
2. 重要结论就近标注来源与日期；
3. 事实、推断和观点分开写；
4. 遇到冲突信息时并列呈现，找不到证据时明确写“暂未核实”。
最后按以下顺序输出：核心结论、关键时间线、横向对比表、详细分析、未来判断、仍待确认的问题。报告需要在10000～30000字之间，语言尽量通俗，不要堆砌资料。
Where the user needs to fill in
【填写产品、公司、人物、技术、行业或事件】
If the user hasn't given everything, first ask for the missing item; don't make it up for them.
The original prompt text comes from Digital Life Kazik; see the acknowledgments in the repository README for the source. Changes to this original text must go through scripts/sync.py; manual edits will be blocked by verify.