research-content-router

Original：🇨🇳 Chinese

Translated

Schedule "research + content production" tasks in A/B/C levels. First define the audience, goal, carrier and perspective, then follow the Research→Synthesis→Content pipeline to output publishable content and evidence chains. It is suitable for writing tasks that require credible conclusions, stable structure and reusable material precipitation.

1installs

Sourcehexbee/hello-skills

Added on2026-03-03

NPX Install

npx skill4agent add hexbee/hello-skills research-content-router

SKILL.md Content (Chinese)

View Translation Comparison →

Research Content Router

When to Use

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

System Objectives

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) Task Grading (A/B/C)

Level A: Confirm before execution

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:

First provide 3 directions + 1 recommended direction
Execute after the user selects the direction

Level B: Execute autonomously before returning

Applicable to:

Topic, audience and format are already clear
The task is mainly expansion, rewriting, structuring and refining

Default actions:

Execute directly
Return with the following content:
- 1 line of "adopted writing assumptions"
- 3 alternative perspectives (for quick direction change)

Level C: Silent archiving

Applicable to:

Link lists, excerpts, term explanations, temporary data storage
The user does not require "immediate release"

Default actions:

Add tags
Write a summary
Archive to the material library (no active disturbance)

2) Six Router Variables (must be completed)

The following variables must be completed for all research/content tasks:

Audience: Who is the content for
Goal: Persuade/action/discussion/bookmark
Carrier: Tweet thread/long article/briefing/script/speech
Perspective: Counterintuitive/methodology/case analysis/comparison review
Evidence level: First-hand source required/optional/not required
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) Three-stage Pipeline

Stage 1: Research (Collection)

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 (Convergence)

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 (Production)

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

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) Atomic Capabilities (9 items)

```
Query Builder
```
: Expand topics into search expressions (Chinese/English/synonyms/time window)
```
Source Triage
```
: Denoise and grade according to
```
S/A/B/⚠️
```
```
Evidence Extractor
```
: Extract key citations and data (with sources)
```
Claim Ledger
```
: Conclusion-evidence comparison table
```
Contrarian Risk
```
: Opposing views and failure conditions
```
Outline Generator
```
: Generate structure according to carrier
```
Hook Factory
```
: Batch generate titles and openings
```
Compression
```
: Compress long content into tweets/short articles/oral broadcasts
```
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) Delivery Format (strong constraint)

Research Deliverables (mandatory)

TL;DR (<=80 words)
Conclusions (3 items)
Evidence (2-4 items per conclusion, including source level)
Risks (>=1 item)
Writing perspectives (3 items)

Tweet Thread Deliverables (mandatory)

5 titles
Thread (8-12 items, each <= 280 words)
Citation/source annotation (when needed)
3 CTAs

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”

Execution Rules

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"

research-content-router

NPX Install

Tags

SKILL.md Content (Chinese)

Research Content Router

When to Use

System Objectives

1) Task Grading (A/B/C)

Level A: Confirm before execution

Level B: Execute autonomously before returning

Level C: Silent archiving

2) Six Router Variables (must be completed)

3) Three-stage Pipeline

Stage 1: Research (Collection)

Stage 2: Synthesis (Convergence)

Stage 3: Content (Production)

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

5) Atomic Capabilities (9 items)

6) Delivery Format (strong constraint)

Research Deliverables (mandatory)

Tweet Thread Deliverables (mandatory)

7) Instruction Template (can be reused directly)

Execution Rules