# claude-real-video

> claude-real-video — huangchihhungleo-claude-real-video. Use this tool when you need to analyze video content with your LLM agent, as it enables watching videos by taking a URL or local file and returning scene-aware keyframes and a timestamped transcript. This tool solves problems related to video understanding, such as extracting key information and identifying important scenes. It accepts video URLs or local files as input and outputs fused keyframes and transcripts, making it ideal for applications requiring local video processing with caching.

Canonical page: https://skillsregistry.net/skills/huangchihhungleo-claude-real-video  
JSON: https://api.skillsregistry.net/v1/skills/huangchihhungleo-claude-real-video

## Description

Lets any LLM agent actually watch videos: a watch_video tool takes a URL or local file and returns scene-aware keyframes fused with a timestamped transcript, processed 100% locally with per-source caching.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/j1bdme3a40)
- **Repository:** <https://github.com/HUANGCHIHHUNGLeo/claude-real-video>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "huangchihhungleo-claude-real-video"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/huangchihhungleo-claude-real-video` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/huangchihhungleo-claude-real-video/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt