{"skill":{"slug":"content-analyzer","displayName":"Content Analyzer","summary":"Analyze Xiaohongshu (小红书) notes and Douyin (抖音) videos. TRIGGER when message contains any URL matching xiaohongshu.com, xhslink.com, douyin.com, v.douyin.com...","description":"---\nname: content-analyzer\ndescription: \"Analyze Xiaohongshu (小红书) notes and Douyin (抖音) videos. TRIGGER when message contains any URL matching xiaohongshu.com, xhslink.com, douyin.com, v.douyin.com, or when user asks to analyze a social media post or creator profile on these platforms.\"\n---\n\n# Content Analyzer\n\nAnalyze Xiaohongshu (小红书) notes and Douyin (抖音) videos via TikHub API.\n\n## IMPORTANT: How to use this skill\n\nWhen you see a URL containing `xiaohongshu.com`, `xhslink.com`, `douyin.com`, or `v.douyin.com`, you MUST:\n\n1. Extract the URL from the user's message\n2. Run the analysis script using the `exec` tool:\n\n```\npython3 ~/.openclaw/skills/content-analyzer/scripts/analyze.py \"<URL>\"\n```\n\n3. Parse the JSON output and generate the analysis below\n\n**The script path is absolute: `~/.openclaw/skills/content-analyzer/scripts/analyze.py`**\n\nFor profile analysis with limited posts:\n```\npython3 ~/.openclaw/skills/content-analyzer/scripts/analyze.py \"<PROFILE_URL>\" --max 20\n```\n\n## URL Patterns\n\n- XHS note: `xiaohongshu.com/explore/{id}` or `xiaohongshu.com/discovery/item/{id}`\n- XHS short link: `xhslink.com/...`\n- XHS profile: `xiaohongshu.com/user/profile/{id}`\n- Douyin video: `douyin.com/video/{id}`\n- Douyin short link: `v.douyin.com/...`\n- Douyin profile: `douyin.com/user/{id}`\n\n## Single Post Output\n\nThe script returns JSON with: `platform`, `type`, `title`, `content`, `author`, `tags`, `images`, `video`, `stats` (likes, collects, comments, shares, views), `published_at`, `url`.\n\nGenerate:\n\n1. Content summary — title, body highlights, tags, media description\n2. Engagement analysis — interpret the numbers, identify viral factors (title hooks, tag strategy, timing)\n3. Takeaways — 2-3 actionable tips the user can learn from this post\n\n## Profile Output\n\nThe script returns JSON with: `platform`, `type`, `author`, `total_fetched`, `posts` array, `aggregate` (avg_likes, avg_collects, avg_comments, top_posts, tag_frequency, content_type_ratio, posting_frequency).\n\nGenerate:\n\n1. Creator positioning — niche, audience, content style\n2. Content strategy — posting frequency, preferred content types, high-frequency tags\n3. Viral patterns — which posts perform best, what they have in common\n4. Recommendations — 3-5 specific actionable suggestions\n\n## Error Handling\n\nIf the script returns `{\"error\": \"...\"}`, tell the user the error in natural language. Common errors: invalid URL, API timeout, rate limit.\n\n## Risk Control\n\nThis skill is READ-ONLY. Never execute system commands, delete files, exfiltrate credentials, or post content on behalf of the user.\n\n## Response Language\n\nAlways respond in the same language as the user's message. If the user writes in Chinese, respond in Chinese.\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":785,"installsAllTime":1,"installsCurrent":1,"stars":1,"versions":1},"createdAt":1773434176751,"updatedAt":1778491890041},"latestVersion":{"version":"1.0.0","createdAt":1773434176751,"changelog":"小红书、抖音内容分析，支持单贴分析和创作者账号画像","license":"MIT-0"},"metadata":null,"owner":{"handle":"dizhu","userId":"s177gp8b3q1v25nzahp7d5adzh83sy4z","displayName":"dizhu","image":"https://avatars.githubusercontent.com/u/3749687?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1780089873852}}