seek-and-analyze-video
Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- seek-and-analyze-video
- risk
- safe
- tags
- [ "video", "ai", "memories", "social-media", "youtube", "tiktok", "analysis" ]
- tools
- [ "claude", "cursor", "gemini" ]
- author
- kennyzheng-builds
- source
- https://github.com/kennyzheng-builds/seek-and-analyze-video
- category
- data-ai
- date_added
- 2026-03-09
- description
- Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence
03 SKILL.md 正文
When to Use
Use 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.
Seek and Analyze Video
Description
This 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).
Overview
The 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.
When to Use This Skill
- Use when analyzing or asking questions about a video from a URL
- Use when searching for videos on TikTok, YouTube, or Instagram by topic, hashtag, or creator
- Use when summarizing meetings, lectures, or webinars from recordings
- Use when building a searchable knowledge base from video content and text memories
- Use when researching social media content trends, influencers, or viral patterns
- Use when analyzing or describing images with AI vision
How It Works
Step 1: Intent Detection
The agent reads the SKILL.md workflow router and matches the user's request to one of 6 intent categories.
Step 2: Reference Loading
The agent loads the appropriate reference file (e.g., video_qa.md for video questions, social_research.md for social media research).
Step 3: Workflow Execution
The agent follows the step-by-step workflow: upload/import -> wait for processing -> analyze/chat -> present results.
Examples
Example 1: Video Q&A
User: "What are the key arguments in this video? https://youtube.com/watch?v=abc123"
Agent: uploads video -> waits for processing -> uses chat_video to ask questions -> presents structured summary
Example 2: Social Media Research
User: "What's trending on TikTok about sustainable fashion?"
Agent: uses search_public to find trending videos -> imports top results -> analyzes content patterns
Example 3: Meeting Notes
User: "Summarize this meeting recording and extract action items"
Agent: uploads recording -> waits -> gets transcript -> uses chat_video for structured summary with action items
Best Practices
- Always wait for video processing to complete before querying
- Use caption_video for quick analysis (no upload needed)
- Use chat_video for deep, multi-turn analysis (requires upload)
- Use search_audio to find specific moments or quotes in a video
- Use memory_add to store important findings for later retrieval
Common Pitfalls
-
Problem: Querying a video before processing completes Solution: Always use the
waitcommand after upload before any analysis -
Problem: Uploading a video when only a quick caption is needed Solution: Use
caption_videofor one-off analysis; only upload for repeated queries
Limitations
- Video processing takes 1-5 minutes depending on length
- Free tier limited to 100 credits
- Social media import requires public content
- Audio search only works on processed videos
Related Skills
- Video analysis tools for one-shot analysis
- Web search skills for non-video content research
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.