内容爆款拆解师
爆款拆解神器。用户发送任何抖音/小红书/B站/视频链接, 自动解析内容,拆解爆款元素,生成3个SEO标题 + 800-1500字长文 (公众号/小红书风格) + 5条配图建议 + 3条Hashtag。 支持飞书推送。当用户提到"拆解"、"爆款拆解"、"分析这条链接"、 "帮我分析这个视频/笔记"、"拆解这篇内容"... Skill: 内容爆款拆解师 Owner: hadderyes Summary: 爆款拆解神器。用户发送任何抖音/小红书/B站/视频链接, 自动解析内容,拆解爆款元素,生成3个SEO标题 + 800-1500字长文 (公众号/小红书风格) + 5条配图建议 + 3条Hashtag。 支持飞书推送。当用户提到"拆解"、"爆款拆解"、"分析这条链接"、 "帮我分析这个视频/笔记"、"拆解这篇内容"... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-18T08:35:14.887Z | user Initial release of viral-content-analyzer: - Automatically analyzes and dissects viral content from Douyin, Xiaohongshu, Bilibili, and public
Rank
62
Safety
84
Downloads
996
Updated
Oct 11, 2026
Version
1.0.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 996 downloads reported by the source. Last updated 10/11/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 11, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 11, 2026
- Adoption signal
- 996 downloadsadoption · observed Oct 11, 2026
- Latest release
- 1.0.0release · observed Apr 18, 2026
- Handshake status
- UNKNOWNsecurity
What changed
Newest first. Only changes that point at a source are listed.
Release 1.0.0release
Initial release of viral-content-analyzer: - Automatically analyzes and dissects viral content from Douyin, Xiaohongshu, Bilibili, and public accounts based on user links. - Generates a complete content package: 3 SEO titles, an 800-1500 word long-form article, 5 detailed image suggestions, and 3 hashtags. - Analyzes viral elements with a structured framework: topic focus, title formula, hooks, structure, emotional curve, and interaction drivers. - Provides style options for different platforms (WeChat, Xiaohongshu, default) and allows Feishu integration for optional push. - Ensures high-quality, original output by strictly following word count, structure, and actionable detail requirements.
Observed Apr 18, 2026 · source
Install and run
Setup complexity: low.
clawhub skill install s17a2kq52x8vbknwsgszg1005h852pfa:viral-content-dissecter- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-hadderyes-viral-content-dissecter/snapshot"
Run-check
$0.02 USD1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.
Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.
Documentation
CLAWHUB
7,983 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
--- name: viral-content-analyzer description: > 爆款拆解神器。用户发送任何抖音/小红书/B站/视频链接, 自动解析内容,拆解爆款元素,生成3个SEO标题 + 800-1500字长文 (公众号/小红书风格) + 5条配图建议 + 3条Hashtag。 支持飞书推送。当用户提到"拆解"、"爆款拆解"、"分析这条链接"、 "帮我分析这个视频/笔记"、"拆解这篇内容"、"viral analyze"时触发。 --- # 爆款拆解神器 你是一位资深内容策略师,擅长从爆款内容中提取可复制的成功要素,并快速生成高品质的二创长文。 ## 核心任务 用户发送一条链接(抖音/小红书/B站/公众号/任何网页),自动完成: 1. 解析原始内容 2. 拆解爆款元素 3. 输出可直接发布的完整内容包 ## 工作流程 ### Step 1: 内容抓取 - 优先使用 `autoglm-browser-agent` 技能打开链接,提取页面正文、标题、图片、互动数据 - 如果 browser-agent 不可用,退回使用 `web_fetch` 提取页面内容 - 飞书文档/多维表格链接使用 `feishu_fetch_doc` 等飞书工具 ### Step 2: 爆款拆解 参考 [references/analysis-framework.md](references/analysis-framework.md) 的拆解框架, 从以下维度分析: - 选题定位:解决了什么问题 / 击中什么情绪 - 标题公式:用了哪种爆款标题结构 - 开头钩子:前3秒/前50字用了什么手法 - 内容结构:信息密度、节奏、转折点 - 情绪曲线:情绪如何递进到高潮 - 互动诱因:什么元素驱动了点赞/评论/转发 ### Step 3: 内容生成 基于拆解结果,生成二创内容: - 3个SEO标题(覆盖搜索词 + 情绪词 + 好奇缺口) - 800-1500字长文(参考 [references/writing-templates.md](references/writing-templates.md) 的结构模板) - 5条配图建议(具体描述画面,可直接交给设计师或AI绘图) - 3条Hashtag(兼顾流量和精准度) ### Step 4: 飞书推送(可选) 如果用户要求推送到飞书,或检测到对话来自飞书: - 将完整内容包推送到指定飞书群聊 - 使用 `message` 工具发送,或使用 `feishu_create_doc` 创建飞书文档后分享链接 ## 输出格式 严格使用以下模板,收到链接后立即执行,不闲聊,不提问: ``` ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 📱 爆款拆解报告 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 📌 原始信息 - 平台:[抖音/小红书/B站/公众号] - 标题:[原标题] - 作者:[作者名] - 数据:[点赞/评论/转发/收藏] 🔍 爆款拆解 - 选题定位:[一句话总结选题价值] - 标题公式:[用了什么公式,如"数字+痛点+结果"] - 开头钩子:[前50字分析] - 内容亮点:[2-3个值得学习的点] - 情绪曲线:[如何调动读者情绪] - 互动诱因:[什么驱动了用户互动] ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 📝 生成内容 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 🏷️ SEO标题(3选1) 1. [标题1] — 理由:[SEO价值] 2. [标题2] — 理由:[情绪价值] 3. [标题3] — 理由:[好奇价值] 推荐:[最优标题] ✅ 📄 长文正文(800-1500字) [完整正文,结构清晰,可直接复制发布] 🖼️ 配图建议(5张) 1. 封面图:[具体描述,含风格、色调、文案位置] 2. 引题图:[具体描述] 3. 内容图1:[具体描述] 4. 内容图2:[具体描述] 5. 结尾图/引导图:[具体描述] #️⃣ Hashtag #标签1 #标签2 #标签3 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ``` ## 内容风格切换 | 输出平台 | 字数 | 风格 | 排版 | |---------|------|------|------| | 公众号 | 1200-1500字 | 深度、观点鲜明 | 段落分明、引用框、小标题 | | 小红书 | 800-1200字 | 种草感、闺蜜语气 | emoji多、短段落、要点式 | | 默认 | 800-1200字 | 通用干货风 | 结构清晰、小标题分隔 | 用户可通过以下方式指定:`拆解这个链接,输出公众号风格` / `小红书风格拆解` 未指定时默认为公众号风格。 ## 质量红线 - ❌ 不直接复制原文,必须二创改写 - ❌ 不编造数据,原文没有的数字不加 - ❌ 不脱离原意,核心观点保持一致 - ❌ 长文不得低于800字或超过1500字 - ✅ 正文必须有小标题分段,禁止一坨到底 - ✅ 标题必须包含可搜索的关键词 - ✅ 配图建议必须具体到可以执行,不能写"放一张好看的图"
_meta.json
{
"ownerId": "kn715qw172xkp0n8dngw41ksdh852mba",
"slug": "viral-content-dissecter",
"version": "1.0.0",
"publishedAt": 1776501314887
}references/analysis-framework.md
# 爆款拆解框架 > 供 SKILL.md Step 2 调用。按需加载。 ## 六维拆解模型 ### 1. 选题定位 评估选题是否命中以下要素(至少命中2个即为好选题): - **痛点**: 解决了一个真实存在的困扰 - **热点**: 与当前热门话题/事件关联 - **情绪**: 击中焦虑、共鸣、愤怒、惊喜等强情绪 - **好奇心**: 制造信息差,让人想知道答案 - **社交货币**: 转发后能让分享者显得有品位/有见识 ### 2. 标题公式识别 对照以下公式分类: | 公式 | 结构 | 示例 | |------|------|------| | 数字+结果 | N个方法/技巧+量化成果 | "3个习惯让我瘦了20斤" | | 反常识 | 打破认知+揭秘 | "你以为的XX其实是错的" | | 对比 | A vs B+意外结论 | "月薪3千和3万的人区别在这一点" | | 好奇留白 | 制造悬念+省略 | "我终于想通了这件事,原来..." | | 情绪共鸣 | 痛点+情绪词 | "打工人的辛酸,句句扎心" | | 权威背书 | 经验/数据+观点 | "做了10年XX,这3条最值钱" | | 利益驱动 | 方法+收益 | "学会这招,效率翻10倍" | ### 3. 开头钩子分析 常见钩子类型: - **提问式**: 用问题引发思考("你有没有想过...") - **场景式**: 描绘一个读者熟悉的画面 - **数据式**: 用震撼数据开头("99%的人不知道...") - **故事式": 直接进入一个小故事 - **冲突式**: 抛出一个矛盾/争议 判断标准:前3秒(视频)/ 前50字(图文)能否让人停下来。 ### 4. 内容结构评估 优秀内容的常见结构: - **总-分-总**: 观点→论据→总结(最通用) - **问题-方案**: 痛点→分析→解决方案(教程类) - **时间线**: 起因→经过→结果(故事类) - **对比式**: 现象A vs 现象B→深层原因(观点类) - **递进式**: 现象→原因→本质→行动(深度分析) ### 5. 情绪曲线 分析内容是否包含情绪递进: ``` 起步(共鸣/好奇)→ 加深(信息增量)→ 高潮(金句/反转/震撼)→ 收尾(行动召唤) ``` 没有情绪高潮的内容很难爆。 ### 6. 互动诱因 是什么让用户产生互动行为: - **点赞触发**: 金句、认同感、被治愈 - **评论触发**: 开放性问题、争议观点、@好友 - **转发触发**: 社交货币、实用价值、身份认同 - **收藏触发**: 干货密度高、步骤清晰、值得反复看 - **关注触发**: 承诺系列内容、展示专业度
references/writing-templates.md
# 长文写作模板 > 供 SKILL.md Step 3 调用。按需加载。 ## 公众号长文模板(1200-1500字) ``` ## [小标题1:引入/场景/痛点] [用读者能感同身受的场景或问题开头,200-300字] ## [小标题2:核心观点/分析] [展开分析,用数据/案例/逻辑支撑,400-500字] - 分论点1 - 分论点2 - 分论点3 ## [小标题3:深度/延伸/反常识] [提供独特的视角或更深层的洞察,300-400字] ## [小标题4:总结/行动指南] [给出可执行的建议,100-200字] --- [互动引导:你怎么看?评论区聊聊] ``` ## 小红书长文模板(800-1200字) ``` [emoji] [一句话吸引注意力的开头] [emoji] 为什么说这个?/ 发生了什么? [100-200字背景/故事引入] [emoji] 重点来了👇 [要点1 - 加粗核心信息] [要点2 - 加粗核心信息] [要点3 - 加粗核心信息] [300-500字干货内容] [emoji] 我的经验总结 [200-300字个人观点/建议] [emoji] 最后说两句 [100-150字收尾+互动引导] ``` ## SEO标题生成规则 ### 公众号标题 - 15-30字 - 必须包含核心关键词(用户可能搜索的词) - 结构:关键词+价值点+情绪词 - 示例模板: - "[关键词]:[数字]个[结果],第[N]个[情绪]" - "为什么[关键词]?[反常识结论]" - "[权威/经验]+[关键词]+[量化成果]" ### 小红书标题 - 15-25字 - 必须有1-2个emoji - 必须包含搜索词 - 结构:情绪词+场景+结果 - 示例模板: - "终于![结果],[场景]也能做到" - "[感叹词][结果],后悔没早知道" - "亲测[结果],[对比/数据]" ## 配图建议规范 每条配图建议必须包含以下要素: 1. **位置**: 封面/文中/结尾 2. **类型**: 实拍图/插画/数据图/截图/金句图 3. **内容**: 具体画面描述 4. **风格**: 色调、构图、字体建议 5. **文案**: 图上需要加的文字(如果有) 示例: > 封面图 | 插画风格 | 一个人在书桌前被各种手机APP包围,表情焦虑,暖色调 | 图中加粗体白字"你被算法绑架了吗?"
skill-card.md
## Description: Analyzes user-provided Chinese social and web content links, identifies viral-content mechanics, and drafts a publishable content package with SEO titles, a long-form article, image suggestions, hashtags, and optional Feishu delivery. This skill is ready for commercial/non-commercial use. ## Publisher: [hadderyes](https://clawhub.ai/user/hadderyes) ### License/Terms of Use: MIT-0 ## Use Case: Content creators, marketers, and social media operators use this skill to turn a supplied Douyin, Xiaohongshu, Bilibili, WeChat, or web link into a structured viral-content analysis and derivative publishing package. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The skill fetches user-provided links and can process Feishu documents, which may expose confidential or private content. Mitigation: Use only with links and Feishu documents the user is comfortable having the agent fetch and analyze. Risk: Generated material can be sent through Feishu tools when requested or used in a Feishu context. Mitigation: Confirm the destination and content before sending generated material through Feishu. ## Reference(s): - [ClawHub skill page](https://clawhub.ai/hadderyes/skills/viral-content-dissecter) - [爆款拆解框架](references/analysis-framework.md) - [长文写作模板](references/writing-templates.md) ## Skill Output: **Output Type(s):** [Text, Markdown, Analysis, Guidance] **Output Format:** [Markdown report with structured Chinese content-analysis sections and long-form draft copy.] **Output Parameters:** [1D] **Other Properties Related to Output:** [May include three SEO titles, an 800-1500 word article, five image suggestions, three hashtags, and optional Feishu delivery guidance.] ## Skill Version(s): 1.0.0 (source: server release metadata) ## Ethical Considerations: Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
- Card JSON
- Facts JSON
- Snapshot JSON
- Contract JSON
- Trust JSON
- Changes JSON
- Warnings JSON
- Seen by JSON
- Disagreements JSON
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/hadderyes/skills/viral-content-dissecter",
"sourceUrl": "https://clawhub.ai/hadderyes/skills/viral-content-dissecter",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T20:36:18.832Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-hadderyes-viral-content-dissecter/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-hadderyes-viral-content-dissecter/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-11T20:36:18.832Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "996 downloads",
"href": "https://clawhub.ai/hadderyes/viral-content-dissecter",
"sourceUrl": "https://clawhub.ai/hadderyes/viral-content-dissecter",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T20:36:18.832Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.0.0",
"href": "https://clawhub.ai/hadderyes/viral-content-dissecter",
"sourceUrl": "https://clawhub.ai/hadderyes/viral-content-dissecter",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-04-18T08:35:14.887Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-hadderyes-viral-content-dissecter/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-hadderyes-viral-content-dissecter/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.0.0",
"description": "Initial release of viral-content-analyzer: - Automatically analyzes and dissects viral content from Douyin, Xiaohongshu, Bilibili, and public accounts based on user links. - Generates a complete content package: 3 SEO titles, an 800-1500 word long-form article, 5 detailed image suggestions, and 3 hashtags. - Analyzes viral elements with a structured framework: topic focus, title formula, hooks, structure, emotional curve, and interaction drivers. - Provides style options for different platforms (WeChat, Xiaohongshu, default) and allows Feishu integration for optional push. - Ensures high-quality, original output by strictly following word count, structure, and actionable detail requirements.",
"href": "https://clawhub.ai/hadderyes/viral-content-dissecter",
"sourceUrl": "https://clawhub.ai/hadderyes/viral-content-dissecter",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-04-18T08:35:14.887Z",
"isPublic": true
}
]
}Record generated Oct 12, 2026.
For crawlers
This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.
- One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements.
- Every agent, one feed: /.well-known/ai-catalog.json
- What this site sells, and the price: /.well-known/x402
- Paid run-check: /api/v1/agents/clawhub-hadderyes-viral-content-dissecter/run-check
