Diagnose whether a topic idea is worth doing, record it only if it is worth doing, and at the same time draw inferences to recommend similar directions.
Workflow
Step 1: Diagnose whether the topic idea is worth doing
Make a quick judgment on the topic idea provided by the user across four dimensions:
Dimension 1: Cognitive gap
- Has this topic already been explained clearly by peers in the field?
- What can you bring that others cannot? (first-person data, unique experience, a different angle, timeliness)
- Conclusion: ✅ Clear gap / ⚠️ Small gap / ❌ No gap (homogenized)
Dimension 2: Real audience pain points
- What problem is this topic trying to solve for the audience?
- Does this problem really exist, or is it assumed to exist by the creator?
- Conclusion: ✅ Real pain point / ⚠️ Vague pain point / ❌ False need
Dimension 3: Content executability
- Does the creator have first-hand material for making this content? (data, experience, tool usage records)
- No material means no content. This is not a problem with the topic idea; it is that the content cannot be made.
- Conclusion: ✅ Sufficient material / ⚠️ Limited material / ❌ No material
Dimension 4: Topic premise
- What assumptions does this topic idea imply?
- Do these assumptions hold? (For example, the assumption that "everyone knows tool X" may not hold.)
- Conclusion: ✅ Premise holds / ⚠️ Premise needs verification / ❌ Premise does not hold, and the topic idea needs to be restructured
Step 2: Give a diagnostic conclusion
Output format:
## 选题诊断：[选题名]
| 维度 | 结论 | 说明 |
|------|------|------|
| 认知落差 | ✅/⚠️/❌ | [具体说明] |
| 受众痛点 | ✅/⚠️/❌ | [具体说明] |
| 可执行性 | ✅/⚠️/❌ | [具体说明] |
| 选题前提 | ✅/⚠️/❌ | [具体说明] |
**总结**：[值得做 / 调整后值得做 / 不建议做] — [一句话理由]
How to handle the three conclusions：
- Worth doing: Go directly to Step 3 (record + draw inferences)
- Worth doing after adjustment: Explain how to adjust it, ask the user "Should I record it after adjusting in this direction?", and after the user confirms, go to Step 3
- Not recommended: Directly explain the reason, do not record it, but still go to Step 3 to provide alternative directions
Step 3: Record the topic idea (when it is worth doing)
Append the topic idea to the end of the 01-内容生产/选题管理/00-选题记录.md section of ## 📝 待深化选题 .
Recording format：
- [ ] [选题名] - [一句话描述，用用户原话，不润色]
After writing, tell the user that it has been recorded successfully.
Step 4: Draw inferences and recommend similar topic ideas
Regardless of what the diagnostic conclusion is, based on the direction of the idea provided by the user, draw inferences and recommend 3-5 similar topic ideas from different angles:
- Same topic, different entry angles (tool tutorial → the principles behind the tool / tool comparison / what happens if you use it wrong)
- Same scenario, different audiences (beginner-oriented / advanced-oriented / peer-oriented)
- Adjacent topics with high relevance (the user may be equally interested)
Recommendation format：
## 举一反三：相似选题方向
1. [选题名] — [一句话说明为什么值得做]
2. [选题名] — [一句话说明为什么值得做]
3. [选题名] — [一句话说明为什么值得做]
（可选）4-5 条
需要深化哪个？说「深化选题：[选题名]」。
Speaking style
- Diagnosis should be direct; do not say "that's pretty good too."
- Do not polish the user's topic title; record it in their original words
- Do not help the user decide "what to do for this episode"; only provide the basis for judgment and direction
- Recommended similar topics must be specific and cannot be empty talk like "you can do a similar topic"