li-recorder

Original：🇨🇳 Chinese

Translated

This skill should be used when the user says phrases like "record a topic", "new topic", "how is this topic", "I have an idea", "help me note this down", or shares a rough content idea that needs evaluation and recording. Even if the user casually mentions a content idea, actively trigger the evaluation process without waiting for the user to explicitly say "record". First, use the five-dimensional logic of dbs-content to diagnose whether the topic is worth doing. Only record it if it is worth doing, and recommend 3-5 similar topics by drawing inferences. Do not trigger: Deepen the topic to generate an outline (use li-topic), directly write scripts (use li-writer), or AI polish or beautify the topic title. Use when the user wants to "record a topic", "log a topic idea", "is this topic worth doing", or shares a rough contentclaise Du.弹应用样子Pr广解除禁 \ 诊断和记录.

4installs

Sourcejiangjiax/li-skills

Added on2026-05-23

NPX Install

npx skill4agent add jiangjiax/li-skills li-recorder

SKILL.md Content (Chinese)

View Translation Comparison →

Topic Diagnosis + Recording System

Diagnose whether a topic is worth doing, record it only if it is, and recommend similar directions by drawing inferences.

Workflow

Step 1: Diagnose whether the topic is worth doing

Make a quick judgment on the user-provided topic from four dimensions:

Dimension 1: Cognitive Gap

Has this topic been clearly explained by peers?
What unique value can you bring that others can't? (First-person data, unique experiences, different perspectives, timeliness)
Conclusion: ✅ Obvious gap / ⚠️ Small gap / ❌ No gap (homogenization)

Dimension 2: Real Audience Pain Points

What problem does this topic attempt to solve for the audience?
Is this problem real, or is it assumed by the creator?
Conclusion: ✅ Real pain point / ⚠️ Vague pain point / ❌ False demand

Dimension 3: Content Executability

Does the creator have first-hand materials for creating this content? (Data, experiences, tool usage records)
Without materials, there is no content. This is not a problem with the topic, but that the content cannot be created.
Conclusion: ✅ Sufficient materials / ⚠️ Limited materials / ❌ No materials

Dimension 4: Topic Premise

What assumptions does this topic imply?
Is this assumption valid? (For example, the assumption "everyone knows Tool X" may not hold)
Conclusion: ✅ Valid premise / ⚠️ Premise needs verification / ❌ Invalid premise, topic needs restructuring

Step 2: Provide Diagnosis Conclusion

Output format:

## Topic Diagnosis: [Topic Name]

| Dimension | Conclusion | Explanation |
|------|------|------|
| Cognitive Gap | ✅/⚠️/❌ | [Specific explanation] |
| Audience Pain Points | ✅/⚠️/❌ | [Specific explanation] |
| Executability | ✅/⚠️/❌ | [Specific explanation] |
| Topic Premise | ✅/⚠️/❌ | [Specific explanation] |

**Summary**: [Worth doing / Worth doing after adjustment / Not recommended] — [One-sentence reason]

Handling methods for the three conclusions:

Worth doing: Proceed directly to Step 3 (Recording + Drawing inferences)
Worth doing after adjustment: Explain how to adjust, ask the user "Shall we record it after adjusting in this direction?", and proceed to Step 3 after user confirmation
Not recommended: Directly explain the reason, do not record it, but still proceed to Step 3 to provide alternative directions

Step 3: Record the Topic (When it is worth doing)

Append the topic to the end of the

## 📝 Topics to be Deepened

section in

01-Content Production/Topic Management/00-Topic Records.md

.

Recording format:

- [ ] [Topic Name] - [One-sentence description, use the user's original words, no polishing]

Inform the user that the recording is successful after writing.

Step 4: Recommend Similar Topics by Drawing Inferences

Regardless of the diagnosis conclusion, based on the user's provided idea direction, recommend 3-5 similar but different-angle topics:

Same topic, different entry angles (Tool tutorial → Principles behind the tool / Tool comparison / Consequences of wrong usage)
Same scenario, different audiences (Beginner-oriented / Advanced-oriented / Peer-oriented)
Adjacent topics with high relevance (Users may also be interested)

Recommendation format:

## Drawing Inferences: Similar Topic Directions

1.GoART [H boolean            coverage-links|[那年 'ways More小组 英文标签：topic-diagnosis, topic-recording, content-creation, idea-management, similar-topic-suggestions
中文标签：选题诊断, 选题记录, 内容创作, 创意管理, 相似选题推荐

需要深化哪个？说「深化选题：[选题名]」。

Speaking Style

Be direct in diagnosis, do not say "it's also good"
Do not polish the user's topic title, record it as original
Do not help the user decide "what to create this issue", only provide judgment basis and directions
Recommended similar topics should be specific, not vague statements like "you can create similar topics"",