domains / data / video-intelligence-analysis / seek-and-analyze-video

seek-and-analyze-video

Skill card

combined

Both copies describe the same Memories.ai LVMM skill, but they are not interchangeable. The first copy is a routing-oriented reference that maps intent to 21 API commands and emphasizes a wait-for-processing step and caption_video vs chat_video trade-offs. The second copy is a workflow-oriented guide that adds API key setup, a marketing-context check, five named modes, and concrete Python-style workflow examples. Crowning one would hide the other's material steps (setup/context in the second; routing/wait semantics in the first).

Repositories

Other copies

Combined skill

---
name: seek-and-analyze-video
description: "Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence"
---

# Seek and Analyze Video

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.

## Before Starting

1. Check for context first: if `marketing-context.md` exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
2. API Setup Required: This skill requires a Memories.ai API key. Guide users to:
   - Visit https://memories.ai to create an account
   - Get API key from dashboard (free tier: 100 credits, Plus: $15/month for 5,000 credits)
   - Set environment variable: `export MEMORIES_API_KEY=your_key_here`
3. Gather context (ask if not provided):
   - Current state: what video content, which platforms, existing libraries or starting fresh
   - Goals: what insights, one-time analysis or persistent knowledge base, individual videos or cross-video research
   - Video-specific context: topics, hashtags, creators, use case, namespace needs

## How It Works

### Step 1: Intent Detection

Read the workflow router and match the user's request to one of the primary modes:
- Quick Video Analysis: one-time analysis without persistent storage
- Social Media Research: discovering and analyzing videos across platforms
- Knowledge Base Building: creating searchable libraries from video content
- Meeting & Lecture Notes: extracting structured notes from recordings
- Memory Management: organizing text insights and cross-video knowledge

### Step 2: Reference Loading

Load the appropriate reference file for the matched intent (e.g., video_qa.md for video questions, social_research.md for social media research).

### Step 3: Workflow Execution

Follow the step-by-step workflow: upload/import -> wait for processing -> analyze/chat -> present results.

## Core Workflows

### Workflow 1: Analyze a Video URL

When to use: User provides a YouTube, TikTok, Instagram, or Vimeo URL.

Process:
1. Validate URL format and platform support
2. Choose analysis mode:
   - Quick analysis: `caption_video(url)` - instant summary, no storage
   - Persistent analysis: `import_video(url)` - index for future queries
3. Wait for processing to complete before querying
4. Extract key information (summary, transcript, action items)
5. Generate structured output

Example:
```python
# Quick analysis (no storage)
result = caption_video("https://youtube.com/watch?v=...")

# Persistent indexing (builds knowledge base)
video_id = import_video("https://youtube.com/watch?v=...")
# Wait for processing
summary = query_video(video_id, "Summarize the key points")
```

### Workflow 2: Social Media Video Research

When to use: User wants to find and analyze videos by topic, hashtag, or creator.

Process:
1. Define search parameters: platform (tiktok, youtube, instagram), query (topic, hashtag, or creator handle), count
2. Execute search: `search_social(platform, query, count)`
3. Import discovered videos for deep analysis
4. Wait for processing
5. Generate competitive insights or trend report

Example:
```python
# Find competitor content
videos = search_social("tiktok", "#SaaSmarketing", count=20)

# Analyze top performers
for video in videos[:5]:
    import_video(video['url'])

# Wait for processing, then cross-video analysis
insights = chat_personal("What content themes are working?")
```

### Workflow 3: Build Video Knowledge Base

When to use: User needs searchable library across multiple videos.

Process:
1. Import videos with tags for organization
2. Store supplementary text memories (notes, insights)
3. Enable cross-video semantic search
4. Query entire library for insights

Example:
```python
# Import video library with tags
import_video(url1, tags=["product-demo", "Q1-2026"])
import_video(url2, tags=["product-demo", "Q2-2026"])

# Store text insights
create_memory("Key insight from demos...", tags=["product-demo"])

# Query across all tagged content
insights = chat_personal("Compare Q1 vs Q2 product demos")
```

### Workflow 4: Extract Meeting Notes

When to use: User needs structured notes from recorded meetings or lectures.

Process:
1. Import meeting recording
2. Wait for processing
3. Request structured extraction:
   - Action items with owners
   - Key decisions made
   - Discussion topics
   - Timestamps for important moments
4. Format as structured output

## 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 `wait` command after upload before any analysis
- Problem: Uploading a video when only a quick caption is needed
  Solution: Use `caption_video` for 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