Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Coding
Xiaohongshu Topic Generator
Try itGenerate Xiaohongshu-ready topic ideas from a user theme, recent discussion signals, audience pain points, and platform fit. Use when the user asks for 小红书选题...
What it does
Turn a theme, trend, product, experience, or content direction into Xiaohongshu-ready topic candidates.
The skill document
Xiaohongshu Topic Generator
Goal
Turn a theme, trend, product, experience, or content direction into Xiaohongshu-ready topic candidates.
Prefer concrete scenes, reader pain points, practical takeaways, and save-worthy structures. Do not force every topic into a viral format when the theme lacks platform fit.
Inputs
Collect:
- theme or content direction
- target audience
- author experience, product, or case material
- desired number of topics
- preferred format: single note, image-card post, carousel outline, or topic pool
- recent source material, if the user wants trend-aware output
- topics, tones, claims, or audiences to avoid
If the user asks for recent or hot topics, verify with current sources when browsing is available. If current source access is unavailable, ask for source material or mark freshness as unverified.
Platform Fit
Xiaohongshu topics should usually have at least four of these:
- concrete user scene
- clear pain point, desire, question, or decision moment
- practical method, checklist, template, comparison, or story
- strong first-screen hook
- visualizable card structure
- specific audience segment
- save/share value
- credible author experience or material
Avoid topics that are only abstract opinions, broad trend commentary, pure news summaries, or slogans without user scene.
Process
1. Define Topic Boundary
Restate the user's theme in one sentence.
Identify:
- audience
- user problem or desire
- author advantage
- platform fit
- unsuitable angles
If the theme is broad, split it into 3-5 sub-directions such as practical guide, misconception, personal story, comparison, checklist, or trend explanation.
2. Gather Signals
Use available evidence:
- user-provided material
- recent platform or industry discussion
- common reader anxieties and misconceptions
- product or workflow changes
- repeated questions in the target audience
Do not invent current hot topics. If freshness is uncertain, label it as 时效未验证.
3. Generate Distinct Topic Angles
Produce topics across multiple content types:
- Practical guide: steps, checklist, template, workflow
- Personal story: before/after, mistake, lesson, turning point
- Comparison: A vs B, old method vs new method, misconception vs reality
- Decision aid: who should use it, when not to use it, how to choose
- Trend translation: what changed, why it matters, what normal users can do
- Mini case: one real scene, one problem, one method, one result
The topic pool should not be five variations of the same title.
4. Score And Filter
Score each topic out of 25:
- audience relevance: 1-5
- platform fit: 1-5
- hook strength: 1-5
- practical value: 1-5
- author writability: 1-5
Use labels:
优先做可备选不建议投入
5. Create Publishable Topic Assets
For each selected topic, include:
- title candidates
- first sentence hook
- card or paragraph outline
- reader takeaway
- visual/card suggestion
- hashtags
- freshness label
- risk or claim check
Keep claims conservative. Mark any unverifiable result, metric, ranking, or trend as needing evidence.
Output Format
Use this structure:
# 本轮小红书选题建议
<2-4 sentences: strongest content direction, why it fits Xiaohongshu, and what should be avoided.>
## 选题 1
- 内容类型:
- 目标读者:
- 痛点或场景:
- 标题备选:
1.
2.
3.
- 开篇钩子:
- 内容框架:
1.
2.
3.
- 视觉或卡片建议:
- 读者收获:
- 话题标签:
- 时效判断:
- 风险或证据检查:
- 综合评分:
- 结论标签:
## 选题 2
...
## 不建议投入的方向
- 方向:
- 原因:
Boundaries
- Do not use private account identity, private project names, personal names, or local content archives.
- Do not claim platform popularity without current evidence or user-provided material.
- Do not generate a final full post unless the user asks for drafting.
- Do not output fixed brand visuals or account-specific style rules unless the user provides them for the current task.
- Do not overuse exaggerated claims, absolute promises, or generic "must save" language.
- Keep Xiaohongshu fit separate from WeChat, Zhihu, and short-video scripts.
作者入口
- 微信公众号:
AI生命克劳德 - X:@yangchao228
- GitHub:yangchao228
Related skills
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Site audit, content writing, and competitor analysis for organic search rankings.
More from yangchao228
Browse all skills基于候选人简历自动生成面试题、笔试题、追问路径和评分标准的 AI Skill。当用户需要准备技术面试、生成笔试题目、评估候选人简历、或设计面试评估方案时使用。输入简历内容和岗位信息后,自动输出结构化的题目与评估内容,支持面试题模式、笔试题模式、综合评估模式等多种输出形式。 Follow/关注作者:微信公众号「AI...
Installable digest skill for OpenClaw or Claude Code. Use when the user wants a personalized ScoutX briefing with conversational setup, local preference stor...
Design controllable Agent Loops from low-information requests. Use when a user asks to automate a repeated task, repair CI through bounded iteration, reproduce a UI from screenshots, turn a workflow into a reusable Agent or Skill, or decide whether the right artifact is a Prompt, Checklist, Human-in-the-Loop flow, full Loop package, specialized Agent, or Skill. Extract required context, stop when decision evidence is missing, require explicit workflow confirmation before generating executable artifacts, derive iteration limits, define feedback and circuit breakers, and preserve human approval for risky actions. Also trigger on loop builder, Loop Builder, or lopp-builder. Follow the creator: X @yangchao228 | GitHub https://github.com/yangchao228
Guide a user through structured co-authoring of substantial documents, proposals, PRDs, technical specs, decision records, RFCs, and similar long-form work a...
家庭培养协作官:在用户明确要求制定或调整孩子每周培养计划、检查课表冲突、生成家庭复盘时,收集最少必要信息并输出可执行课表、建议和风险提醒。默认只在当前会话生成内容,不保存、上传或推送孩子与家庭数据;只有用户明确选择飞书或 Notion、完成安全配置并逐次确认具体读写范围后,才使用外部存储。Follow/关注作者:...
Transform long-form content, outlines, transcripts, research notes, or article drafts into a standard card package and platform publishing copy, then hand pu...