Install any skill in seconds. Free to start, no credit card required.
Get Started Free →生成小红书热点选题和内容创意。当用户提到"热点选题"、"内容创意"、"小红书选题"、"trending topics"、"content ideas"、"热门话题"、"爆款选题"时使用。适用于品牌社媒运营、内容策划、热点借势营销场景。
.claude/skills/hot-topic-ideator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-13 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
| case-19 | ✗→✓ | ▲ Improved | — | — |
基于小红书真实数据,为品牌生成5-10个高质量热点选题创意,输出为专业 HTML 报告并转换为 PDF。
使用示例:
用户:帮雪碧生成小红书热点选题
用户:给元气森林做5个内容创意
用户:为喜茶策划热点借势内容bashexport CHATDAM_API_TOKEN="YOUR_TOKEN_HERE"
若用户只提供品牌名称,需收集以下信息:
若用户已提供详细信息,直接进入Step 2。
基于品牌DNA,生成5-8个搜索关键词:
关键词公式:
| 类型 | 公式 | 示例 | |------|------|------| | 品牌+品类 | 品牌名] 产品类型] | 雪碧 气泡水 | | 品牌+场景 | 品牌名] 使用场景] | 雪碧 火锅 | | 品牌+情绪 | 品牌名] 情感词] | 雪碧 爽快 | | 品类+热点 | 品类] 潜在热词] | 碳酸饮料 搞抽象 | | 场景+趋势 | 消费场景] 流行词] | 聚餐 氛围感 |
输出: 5-8个关键词列表
对每个关键词调用API:
bashcurl --request GET 'https://asset.tezign.com/chatdam/api/notes/search?keyword=[KEYWORD_URL_ENCODED]' \ --header "Authorization: Bearer ${CHATDAM_API_TOKEN}" \ --header 'Content-Type: application/json'
响应结构:
json{ "data": { "keyword": "雪碧 火锅", "notes": [ { "noteId": "69800480000000000e03c5b1", "title": "火锅配雪碧太爽了", "description": "辣到飞起的时候来一口冰爽雪碧 #火锅 #雪碧 #聚餐", "likedCount": 1205, "commentCount": 43, "collectedCount": 89, "sharedCount": 12 } ], "total": 20 } }
数据处理:
为每篇笔记计算互动分数:
engagement_score = likedCount + (commentCount × 2) + (collectedCount × 3) + (sharedCount × 1.5)从description中提取话题标签(#xxx格式)
对每个关键词的前3篇高互动笔记,获取详情:
bashcurl --request GET 'https://asset.tezign.com/chatdam/api/notes/detail?noteId=[NOTE_ID]' \ --header "Authorization: Bearer ${CHATDAM_API_TOKEN}"
分析要点:
汇总所有提取的话题标签,计算得分:
话题得分 = (出现频次 × 0.4) + (关联笔记平均互动 × 0.6)筛选Top 10话题,评估维度:
| 维度 | 权重 | 评分标准 | |------|------|----------| | 品牌相关性 | 30% | 与品牌价值观/场景的契合度 | | 用户互动量 | 25% | 关联笔记的平均互动表现 | | 内容可复制性 | 20% | 品牌执行的难易程度 | | 趋势热度 | 15% | 话题的增长势头 | | 竞品空白度 | 10% | 竞品是否已切入 |
调用官方热榜API验证话题热度:
bashcurl --request GET 'https://asset.tezign.com/chatdam/api/hot-trends?limit=20' \ --header "Authorization: Bearer ${CHATDAM_API_TOKEN}"
验证结果标记:
对高分话题,以话题为关键词再次搜索:
bashcurl --request GET 'https://asset.tezign.com/chatdam/api/notes/search?keyword=%23搞抽象' \ --header "Authorization: Bearer ${CHATDAM_API_TOKEN}"
分析:
基于前述分析结果,生成专业 HTML 报告,包含5-10个热点选题。
报告整体结构如下,每个选题需包含完整信息:
基于品牌属性,为报告选取合适的设计风格。以下为设计框架:
社媒热点选题报告面向品牌运营团队和决策者,视觉风格需兼顾数据专业性和社交媒体活力感——既有策略报告的严肃信服力,又有社媒内容的灵动气质。
设计方向参考:
色彩策略:
排版层级:
信息密度:
用最有力的专业方式呈现最有价值的洞察。报告视觉语言应使用成熟专业的手法(编辑设计、信息图表美学),而非廉价的技术感装饰(霓虹渐变、3D效果、花哨特效)。
关键原则:
色彩策略:
排版层级:
信息密度与阅读效率:
<!DOCTYPE html> 开头GET https://asset.tezign.com/chatdam/api/notes/search?keyword=[ENCODED_KEYWORD]
Header: Authorization: Bearer ${CHATDAM_API_TOKEN}
返回: 20篇笔记,含标题、描述、互动数据GET https://asset.tezign.com/chatdam/api/notes/detail?noteId=[NOTE_ID]
Header: Authorization: Bearer ${CHATDAM_API_TOKEN}
返回: 完整笔记内容、话题标签、详细数据GET https://asset.tezign.com/chatdam/api/hot-trends?limit=20
Header: Authorization: Bearer ${CHATDAM_API_TOKEN}
返回: 官方热榜Top20,含热度值和排名变化创建 HTML 报告文件,保存到指定路径:
{base_dir}/{品牌名}-hot-topics/report.htmlHTML 报告内容包括:
技术要求:
<!DOCTYPE html> 开头的完整 HTML 文件使用转换脚本生成最终 PDF:
bashuv run {baseDir}/scripts/html_to_pdf.py --html {base_dir}/{品牌名}-hot-topics/report.html --output {base_dir}/{品牌名}-hot-topics/report.pdf
脚本会:
MEDIA: 行用于自动附件API调用失败:
笔记数量不足:
热榜API不可用:
以下为报告 HTML 的骨架结构示意(实际生成时需填充真实数据和完整样式):
html<!DOCTYPE html> <html lang="zh-CN"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>[品牌名] 小红书热点选题 Brief</title> <script src="https://cdn.tailwindcss.com"></script> <style> /* 自定义字体和基础样式 */ body { font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", sans-serif; background: #fafafa; color: #1a1a1a; } /* 打印优化 */ @media print { body { background: white; } .page-break { page-break-before: always; } } </style> </head> <body class="min-h-screen"> <!-- 封面区域 --> <header class="bg-white border-b border-gray-200 px-8 py-12 mb-8"> <p class="text-sm tracking-widest text-gray-400 uppercase mb-4">Xiaohongshu Content Strategy</p> <h1 class="text-4xl font-bold text-gray-900 mb-2">[品牌名]</h1> <h2 class="text-xl font-light text-gray-500 mb-8">小红书热点选题 Brief</h2> <div class="grid grid-cols-4 gap-6 mt-8"> <div class="border-l-2 border-gray-900 pl-4"> <p class="text-2xl font-bold">6</p> <p class="text-xs text-gray-500 mt-1">搜索关键词</p> </div> <div class="border-l-2 border-gray-900 pl-4"> <p class="text-2xl font-bold">120</p> <p class="text-xs text-gray-500 mt-1">分析笔记</p> </div> <div class="border-l-2 border-gray-900 pl-4"> <p class="text-2xl font-bold">85</p> <p class="text-xs text-gray-500 mt-1">提取话题</p> </div> <div class="border-l-2 border-gray-900 pl-4"> <p class="text-2xl font-bold">3</p> <p class="text-xs text-gray-500 mt-1">热榜验证</p> </div> </div> </header> <!-- 选题概览表 --> <section class="bg-white mx-8 mb-8 p-6 border border-gray-100"> <h3 class="text-lg font-bold text-gray-900 mb-4">选题概览</h3> <table class="w-full text-sm"> <thead> <tr class="border-b-2 border-gray-900"> <th class="text-left py-2 font-medium">#</th> <th class="text-left py-2 font-medium">选题</th> <th class="text-left py-2 font-medium">热度</th> <th class="text-left py-2 font-medium">执行难度</th> <th class="text-left py-2 font-medium">推荐度</th> </tr> </thead> <tbody> <!-- 由实际数据填充 --> <tr class="border-b border-gray-100"> <td class="py-3 font-bold">1</td> <td class="py-3">选题标题示例</td> <td class="py-3">⭐⭐⭐⭐⭐</td> <td class="py-3">中</td> <td class="py-3">★★★★★</td> </tr> </tbody> </table> </section> <!-- 选题详情卡片(重复N个) --> <section class="mx-8 mb-8"> <article class="bg-white border border-gray-100 p-6 mb-6"> <div class="flex items-center justify-between mb-4"> <h3 class="text-xl font-bold text-gray-900">选题 1: 选题标题</h3> <span class="text-xs px-3 py-1 bg-gray-900 text-white">✅ 官方热榜</span> </div> <div class="grid grid-cols-3 gap-4 mb-4 text-sm"> <div> <p class="text-gray-400 text-xs mb-1">关联话题</p> <p>#话题1 #话题2 #话题3</p> </div> <div> <p class="text-gray-400 text-xs mb-1">数据支撑</p> <p>XX篇相关笔记,平均互动XX</p> </div> <div> <p class="text-gray-400 text-xs mb-1">内容形式</p> <p>图文 / 6张图</p> </div> </div> <div class="mb-4"> <p class="text-gray-400 text-xs mb-1">创意概念</p> <p class="text-lg font-medium">一句话核心创意描述</p> </div> <div class="mb-4"> <p class="text-gray-400 text-xs mb-1">创意阐释</p> <p class="text-sm text-gray-700 leading-relaxed">详细说明创意逻辑和品牌结合点...</p> </div> <div class="mb-4"> <p class="text-gray-400 text-xs mb-1">互动设计</p> <p class="text-sm text-gray-700">如何引导用户互动,评论区玩法...</p> </div> <div class="mb-4"> <p class="text-gray-400 text-xs mb-1">执行要点</p> <ol class="text-sm text-gray-700 list-decimal list-inside space-y-1"> <li>关键执行点1</li> <li>关键执行点2</li> <li>关键执行点3</li> </ol> </div> <div class="border-t border-gray-100 pt-3 text-xs text-gray-400"> 参考笔记: Note ID xxx | 互动: xxx | 成功要素: xxx </div> </article> </section> <!-- 数据来源说明 --> <footer class="mx-8 mb-12 py-4 border-t border-gray-200 text-xs text-gray-400"> <p>数据来源:小红书笔记搜索API / 官方热榜API | 搜索关键词:xxx, xxx | 分析笔记数:xxx篇</p> </footer> </body> </html>
以上仅为骨架参考,实际生成时需要:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-25 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-24 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted, and 22 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +48 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.