[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-4e9d94ee-7fb1-4b9d-b9b2-28ac7fe4d762":3,"$fzgUHPEnLY0_npEICZLPMLGkQR1-OmJYRWI3CZ51oAdg":43},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":34},"4e9d94ee-7fb1-4b9d-b9b2-28ac7fe4d762","seek-and-analyze-video","使用Memories.ai大型视觉记忆模型搜索和分析视频内容，实现持续的视频智能","cat_design_graphic","mod_design","sickn33,design","---\nname: seek-and-analyze-video\ndescription: \"Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence\"\ncategory: data-ai\nrisk: safe\nsource: \"https:\u002F\u002Fgithub.com\u002Fkennyzheng-builds\u002Fseek-and-analyze-video\"\ndate_added: \"2026-03-09\"\nauthor: kennyzheng-builds\ntags: [video, ai, memories, social-media, youtube, tiktok, analysis]\ntools: [claude, cursor, gemini]\n---\n\n## When to Use\nUse this skill when the user wants to search for, import, or analyze video content from TikTok, YouTube, or Instagram, summarize meetings or lectures from recordings, build a searchable knowledge base from video content, or research social media trends and creators.\n\n# Seek and Analyze Video\n\n## Description\n\nThis skill enables AI agents to search, import, and analyze video content using Memories.ai's Large Visual Memory Model (LVMM). Unlike one-shot video analysis tools, it provides persistent video intelligence -- videos are indexed once and can be queried repeatedly across sessions. Supports social media import (TikTok, YouTube, Instagram), meeting summarization, knowledge base building, and cross-video Q&A via Memory Augmented Generation (MAG).\n\n## Overview\n\nThe skill wraps 21 API commands into workflow-oriented reference guides that agents load on demand. A routing table in SKILL.md maps user intent to the right workflow automatically.\n\n## When to Use This Skill\n\n- Use when analyzing or asking questions about a video from a URL\n- Use when searching for videos on TikTok, YouTube, or Instagram by topic, hashtag, or creator\n- Use when summarizing meetings, lectures, or webinars from recordings\n- Use when building a searchable knowledge base from video content and text memories\n- Use when researching social media content trends, influencers, or viral patterns\n- Use when analyzing or describing images with AI vision\n\n## How It Works\n\n### Step 1: Intent Detection\n\nThe agent reads the SKILL.md workflow router and matches the user's request to one of 6 intent categories.\n\n### Step 2: Reference Loading\n\nThe agent loads the appropriate reference file (e.g., video_qa.md for video questions, social_research.md for social media research).\n\n### Step 3: Workflow Execution\n\nThe agent follows the step-by-step workflow: upload\u002Fimport -> wait for processing -> analyze\u002Fchat -> present results.\n\n## Examples\n\n### Example 1: Video Q&A\n\n```\nUser: \"What are the key arguments in this video? https:\u002F\u002Fyoutube.com\u002Fwatch?v=abc123\"\nAgent: uploads video -> waits for processing -> uses chat_video to ask questions -> presents structured summary\n```\n\n### Example 2: Social Media Research\n\n```\nUser: \"What's trending on TikTok about sustainable fashion?\"\nAgent: uses search_public to find trending videos -> imports top results -> analyzes content patterns\n```\n\n### Example 3: Meeting Notes\n\n```\nUser: \"Summarize this meeting recording and extract action items\"\nAgent: uploads recording -> waits -> gets transcript -> uses chat_video for structured summary with action items\n```\n\n## Best Practices\n\n- Always wait for video processing to complete before querying\n- Use caption_video for quick analysis (no upload needed)\n- Use chat_video for deep, multi-turn analysis (requires upload)\n- Use search_audio to find specific moments or quotes in a video\n- Use memory_add to store important findings for later retrieval\n\n## Common Pitfalls\n\n- **Problem:** Querying a video before processing completes\n  **Solution:** Always use the `wait` command after upload before any analysis\n\n- **Problem:** Uploading a video when only a quick caption is needed\n  **Solution:** Use `caption_video` for one-off analysis; only upload for repeated queries\n\n## Limitations\n\n- Video processing takes 1-5 minutes depending on length\n- Free tier limited to 100 credits\n- Social media import requires public content\n- Audio search only works on processed videos\n\n## Related Skills\n\n- Video analysis tools for one-shot analysis\n- Web search skills for non-video content research\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,180,1454,"2026-05-16 13:38:32",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"设计创意","design","mdi-palette-outline","UI 设计、生成艺术、品牌视觉等创意 Skill",3,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":32,"skillCount":33,"createdAt":26},"视觉创意","graphic","mdi-brush","海报、Logo、插画等视觉创作",2,48,[35],{"id":36,"skillId":4,"version":37,"fileName":38,"fileSize":39,"filePath":40,"fileHash":41,"manifest":42,"createdAt":19},"ccf1c63e-d21b-4921-8bda-a7f9a5bfd79b","1.0.0","seek-and-analyze-video.zip",1828,"uploads\u002Fskills\u002F4e9d94ee-7fb1-4b9d-b9b2-28ac7fe4d762\u002Fseek-and-analyze-video.zip","a141fdefce48efa9f86e3716cd4e678ea897c50c780d31a4904e107f5194af27","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":3986}]",{"code":44,"message":45,"data":46},200,"success",{"items":47,"stats":48,"page":51},[],{"averageRating":49,"totalRatings":49,"ratingCounts":50},0,[49,49,49,49,49],{"limit":52,"offset":49,"hasMore":53,"nextOffset":52,"ratedOnly":16},15,false]