Back to Details

research-content-router

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Research Content Router

Research Content Router

何时使用

When to Use

当用户提出以下需求时触发本技能：
  • 研究某个主题并产出内容（推文、长文、简报、脚本等）
  • 需要“结论 + 证据链”而不是纯资料堆
  • 需要在“传播、可信度、转化”之间选择内容方向
  • 希望把研究产出沉淀为可复用素材
Trigger this skill when the user puts forward the following demands:
  • Research a certain topic and produce content (tweets, long articles, briefings, scripts, etc.)
  • Need "conclusion + evidence chain" instead of pure data stacking
  • Need to choose content direction among "communication, credibility, conversion"
  • Hope to convert research outputs into reusable materials

系统目标

System Objectives

  • 用最少确认次数拿到可发布内容
  • 将研究转化为“结论 + 证据链 + 可复用素材库”
  • 先收敛选题/角度/受众/格式，再写作
  • Obtain publishable content with the minimum number of confirmations
  • Convert research into "conclusion + evidence chain + reusable material library"
  • First define the topic/perspective/audience/format before writing

1) 任务分级（A/B/C）

1) Task Grading (A/B/C)

A 级：先确认再执行

Level A: Confirm before execution

满足任一即 A：
  • 需要联网检索、引用来源、或对外发布研究结论
  • 涉及观点立场、攻击性评价、法律合规、投资建议
  • 要求长内容（>800 字或 >10 条推）或系列内容
  • 需要用户私域数据（笔记/文档/项目/客户信息）
默认动作：
  1. 先给 3 个方向 + 推荐 1 个
  2. 用户选定方向后再执行
Classified as Level A if any of the following is met:
  • Require online search, source citation, or public release of research conclusions
  • Involve viewpoints and positions, aggressive comments, legal compliance, investment advice
  • Require long content (>800 words or >10 tweets) or series content
  • Require user's private domain data (notes/documents/projects/customer information)
Default actions:
  1. First provide 3 directions + 1 recommended direction
  2. Execute after the user selects the direction

B 级：自主执行后返回

Level B: Execute autonomously before returning

适用：
  • 主题、受众、格式已明确
  • 任务以扩写、改写、结构化、提炼为主
默认动作：
  1. 直接执行
  2. 返回时附带：
    • 1 行“采用的写作假设”
    • 3 个可替代角度（便于快速改向）
Applicable to:
  • Topic, audience and format are already clear
  • The task is mainly expansion, rewriting, structuring and refining
Default actions:
  1. Execute directly
  2. Return with the following content:
    • 1 line of "adopted writing assumptions"
    • 3 alternative perspectives (for quick direction change)

C 级：静默归档

Level C: Silent archiving

适用：
  • 链接清单、摘录、术语解释、资料暂存
  • 用户未要求“立即发布”
默认动作：
  1. 打标签
  2. 写摘要
  3. 归档到素材库（不主动打扰）
Applicable to:
  • Link lists, excerpts, term explanations, temporary data storage
  • The user does not require "immediate release"
Default actions:
  1. Add tags
  2. Write a summary
  3. Archive to the material library (no active disturbance)

2) Router 六变量（必须补齐）

2) Six Router Variables (must be completed)

研究/内容任务统一补齐以下变量：
  1. 受众：写给谁
  2. 目标：相信/行动/讨论/收藏
  3. 载体：推文线程/长文/简报/脚本/演讲稿
  4. 角度：反常识/方法论/案例拆解/对比评测
  5. 证据级别：一手源必须/可选/不需要
  6. 尺度：长度、数量、交付时间
执行规则：
  • A 级：将 1-6 转成可选项让用户点选
  • B 级：缺失项可自行假设，但需明确写出假设
  • C 级：只存档，不追问
The following variables must be completed for all research/content tasks:
  1. Audience: Who is the content for
  2. Goal: Persuade/action/discussion/bookmark
  3. Carrier: Tweet thread/long article/briefing/script/speech
  4. Perspective: Counterintuitive/methodology/case analysis/comparison review
  5. Evidence level: First-hand source required/optional/not required
  6. Scale: Length, quantity, delivery time
Execution rules:
  • Level A: Convert 1-6 into options for users to select
  • Level B: Missing items can be assumed autonomously, but the assumptions must be clearly stated
  • Level C: Only archive, no further inquiry

3) 三段式流水线

3) Three-stage Pipeline

Stage 1: Research（搜集）

Stage 1: Research (Collection)

必须输出：
  • 结论候选 3-5 条
  • 每条结论对应证据（链接/原话/数据）
  • 证据分级： 
    • S
      一手源（财报/论文/官方文档/原始数据）
    • A
      权威二手源（主流媒体/机构报告）
    • B
      一般二手源（博客/社区）
    • ⚠️
      未证实来源（传言/未核实自媒体）
硬规则：
  • 没有证据的观点不得进入 Stage 2
Required outputs:
  • 3-5 candidate conclusions
  • Evidence corresponding to each conclusion (link/verbatim quote/data)
  • Evidence grading: 
    • S
      First-hand source (financial report/paper/official document/raw data)
    • A
      Authoritative second-hand source (mainstream media/institutional report)
    • B
      General second-hand source (blog/community)
    • ⚠️
      Unverified source (rumor/unverified self-media)
Hard rules:
  • Opinions without evidence are not allowed to enter Stage 2

Stage 2: Synthesis（收敛）

Stage 2: Synthesis (Convergence)

必须输出：
  • 核心论点（1 句话）
  • 支撑点 3 条（每条都要挂证据）
  • 反方风险 1 条（强制项）
硬规则：
  • 缺少“反方风险”则判定失败，必须重做
Required outputs:
  • Core argument (1 sentence)
  • 3 supporting points (each must be attached with evidence)
  • 1 counterparty risk (mandatory item)
Hard rules:
  • Lack of "counterparty risk" will be judged as failure and must be redone

Stage 3: Content（生产）

Stage 3: Content (Production)

默认交付：
  • 主版本（按选定载体）
  • 备选标题 5 个
  • 结尾 CTA 3 个（提问/收藏引导/讨论引导）
  • 可复用素材：
    • 金句 10 条
    • 类比 3 个
    • 图表建议 2 个
Default deliverables:
  • Main version (according to the selected carrier)
  • 5 alternative titles
  • 3 closing CTAs (question/bookmark guide/discussion guide)
  • Reusable materials:
    • 10 golden quotes
    • 3 analogies
    • 2 chart suggestions

4) A 级确认卡（固定三选一）

4) Level A Confirmation Card (fixed one out of three)

当用户说“研究某主题/写内容”时，先返回：
  • 方向 A（更快传播）：反常识结论 + 强观点
  • 方向 B（更强信任）：证据链 + 一手源引用
  • 方向 C（更能转化）：方法论/清单/框架，可直接照做
并附一句推荐：
  • 默认推荐 B：研究情报任务中，可信度决定复用价值
When the user says "research a certain topic/write content", return first:
  • Direction A (faster dissemination): Counterintuitive conclusion + strong viewpoint
  • Direction B (higher trust): Evidence chain + first-hand source citation
  • Direction C (higher conversion): Methodology/checklist/framework, can be followed directly
Attach a recommendation:
  • Default recommendation B: In research intelligence tasks, credibility determines reuse value

5) 原子能力（9 个）

5) Atomic Capabilities (9 items)

  1. Query Builder
    ：主题扩展为检索式（中英/同义词/时间窗）
  2. Source Triage
    ：按 
    S/A/B/⚠️
    去噪分级
  3. Evidence Extractor
    ：抽取关键引用与数据（带出处）
  4. Claim Ledger
    ：结论-证据对照表
  5. Contrarian Risk
    ：反方观点与失败条件
  6. Outline Generator
    ：按载体产出结构
  7. Hook Factory
    ：批量生成标题与开头
  8. Compression
    ：长内容压缩成推文/短文/口播
  9. Repurpose
    ：研究一稿多用（推文→长文→脚本→邮件）
要求：
  • 每个能力都要固定输入/输出格式，保证可堆叠
  1. Query Builder
    : Expand topics into search expressions (Chinese/English/synonyms/time window)
  2. Source Triage
    : Denoise and grade according to 
    S/A/B/⚠️
  3. Evidence Extractor
    : Extract key citations and data (with sources)
  4. Claim Ledger
    : Conclusion-evidence comparison table
  5. Contrarian Risk
    : Opposing views and failure conditions
  6. Outline Generator
    : Generate structure according to carrier
  7. Hook Factory
    : Batch generate titles and openings
  8. Compression
    : Compress long content into tweets/short articles/oral broadcasts
  9. Repurpose
    : One research draft for multiple uses (tweet → long article → script → email)
Requirements:
  • Each capability must have a fixed input/output format to ensure stackability

6) 交付格式（强约束）

6) Delivery Format (strong constraint)

研究交付（必选）

Research Deliverables (mandatory)

  • TL;DR（<=80 字）
  • 结论（3 条）
  • 证据（每条结论 2-4 条，含来源等级）
  • 风险（>=1 条）
  • 可写角度（3 个）
  • TL;DR (<=80 words)
  • Conclusions (3 items)
  • Evidence (2-4 items per conclusion, including source level)
  • Risks (>=1 item)
  • Writing perspectives (3 items)

推文线程交付（必选）

Tweet Thread Deliverables (mandatory)

  • 标题 5 个
  • Thread（8-12 条，每条 <= 280 字）
  • 引用/出处标注（需要时）
  • CTA 3 个
  • 5 titles
  • Thread (8-12 items, each <= 280 words)
  • Citation/source annotation (when needed)
  • 3 CTAs

7) 指令模板（可直接复用）

7) Instruction Template (can be reused directly)

text
主题：{X}
受众：{创业者/开发者/投资人}
目标：{收藏/讨论/转发}
载体：{推文线程 10 条}
证据级别：{必须一手源/可选/不需要}
约束：{语气/禁忌/长度}
输出：按“研究交付 + 推文线程交付”
text
主题：{X}
受众：{创业者/开发者/投资人}
目标：{收藏/讨论/转发}
载体：{推文线程 10 条}
证据级别：{必须一手源/可选/不需要}
约束：{语气/禁忌/长度}
输出：按“研究交付 + 推文线程交付”

执行守则

Execution Rules

  • 永远先分级，再决定是否提问
  • 永远先收敛变量，再进入写作
  • 永远保留反方风险，防单边结论
  • 永远保持“可发布 + 可追溯 + 可复用”
  • Always grade first, then decide whether to ask questions
  • Always define variables first, then start writing
  • Always retain counterparty risk to prevent one-sided conclusions
  • Always maintain "publishable + traceable + reusable"