von jordanrendric · jordanrendric/claude-video-vision
Make Claude actually understand a video — frames + transcript + scene segmentation, fed in a token-efficient layout.
The skill takes a video file or URL, extracts keyframes (scene-aware), aligns transcript segments, and presents the bundle to Claude for QA, summary, or content extraction. Smart-sampling avoids blowing the context window.
%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"claude-video-vision": {
"command": "git",
"args": [
"clone",
"https://github.com/jordanrendric/claude-video-vision"
],
"_inferred": true
}
}
}Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.
{
"mcpServers": {
"claude-video-vision": {
"command": "git",
"args": [
"clone",
"https://github.com/jordanrendric/claude-video-vision"
],
"_inferred": true
}
}
}Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.
{
"mcpServers": {
"claude-video-vision": {
"command": "git",
"args": [
"clone",
"https://github.com/jordanrendric/claude-video-vision"
],
"_inferred": true
}
}
}Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".
{
"mcpServers": {
"claude-video-vision": {
"command": "git",
"args": [
"clone",
"https://github.com/jordanrendric/claude-video-vision"
],
"_inferred": true
}
}
}Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.
{
"mcpServers": [
{
"name": "claude-video-vision",
"command": "git",
"args": [
"clone",
"https://github.com/jordanrendric/claude-video-vision"
]
}
]
}Continue nutzt ein Array von Serverobjekten statt einer Map.
{
"context_servers": {
"claude-video-vision": {
"command": {
"path": "git",
"args": [
"clone",
"https://github.com/jordanrendric/claude-video-vision"
]
}
}
}
}In context_servers hinzufügen. Zed lädt beim Speichern neu.
claude mcp add claude-video-vision -- git clone https://github.com/jordanrendric/claude-video-visionEinzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.
Wann einsetzen: Conference talk just dropped; you want notes without watching it.
Ergebnis: Targeted understanding without re-watching.
Save the structured note output for later reference
| Werkzeug | Eingaben | Wann aufrufen | Kosten |
|---|---|---|---|
| ingest | (see docs) | Pull video + transcript | 1 call |
| query | (see docs) | Scope-aware question answering | 1 call |
fs-read fs-writeprocess private video without consentTranscript misalignedLower scene-segmentation threshold; transcript may be off due to music
| Alternative | Wann stattdessen | Kompromiss |
|---|---|---|
| Manual notes | Talk is short | Doesn't scale to many videos |