# mengtang1114-forks/video-use architecture

> Architecture diagram of the GitHub repository mengtang1114-forks/video-use, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mengtang1114-forks/video-use
- Repository: https://github.com/mengtang1114-forks/video-use

## Overview

video-use is an agent-guided video editing workflow: the user supplies footage and approves an edit strategy; an agent uses transcripts and visual drill-downs to create an edit decision list (EDL), renders and evaluates the result, then returns a final video. The README documents the workflow and capabilities; sampled helper code supports transcription, transcript packing, timeline views, and rendering. The orchestration and several documented features are described but not sampled, so those links reflect documentation rather than verified implementation calls.

Main entry points: [`helpers/render.py`](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/render.py) (Video rendering), [`helpers/transcribe.py`](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/transcribe.py) (Transcription), [`SKILL.md`](https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md) (Cut evaluation), [`helpers/timeline_view.py`](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/timeline_view.py) (Visual drill-down)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workflow["Editing workflow"]
  node_skill["Editing rules<br/>[SKILL.md]"]
  node_inventory["Inventory and strategy<br/>[SKILL.md]"]
  node_approval["Strategy approval<br/>[SKILL.md]"]
  node_edl["Edit decision list"]
  node_memory["Project memory"]
  node_evaluation["Cut evaluation<br/>[SKILL.md]"]
  node_final["Final video"]
end

subgraph group_transcripts["Speech and review"]
  node_transcribe["Transcription<br/>[transcribe.py]"]
  node_batch["Batch transcription"]
  node_transcripts["Word transcripts"]
  node_packing["Transcript packing"]
  node_packed["Packed transcript"]
  node_timeline["Visual drill-down<br/>[timeline_view.py]"]
end

subgraph group_rendering["Render and polish"]
  node_render["Video rendering<br/>[render.py]"]
  node_grade["Color grading<br/>[grade.py]"]
  node_overlays["Animation overlays"]
end

subgraph group_integrations["External integrations"]
  node_scribe["ElevenLabs Scribe"]
  node_ffmpeg["FFmpeg tools"]
  node_engines["Overlay engines"]
end

node_user(("Editor"))
node_agent(("Editing agent"))
node_footage["Source footage"]

node_user -->|"supplies"| node_footage
node_user -->|"requests edit"| node_agent
node_agent -->|"follows"| node_skill
node_agent -->|"inspects"| node_inventory
node_footage -->|"inventoried by"| node_inventory
node_agent -->|"proposes strategy"| node_approval
node_user -->|"approves"| node_approval
node_footage -->|"transcribed from"| node_batch
node_footage -->|"transcribed from"| node_transcribe
node_batch -->|"dispatches"| node_transcribe
node_transcribe -->|"extracts audio"| node_ffmpeg
node_transcribe -->|"uploads audio"| node_scribe
node_transcribe -->|"writes"| node_transcripts
node_transcripts -->|"reads"| node_packing
node_packing -->|"writes"| node_packed
node_agent -->|"reads"| node_packed
node_agent -->|"requests view"| node_timeline
node_footage -->|"frames and audio"| node_timeline
node_transcripts -->|"labels view"| node_timeline
node_agent -->|"authors"| node_edl
node_edl -->|"drives render"| node_render
node_render -->|"invokes"| node_ffmpeg
node_render -->|"applies grading"| node_grade
node_render -->|"composites"| node_overlays
node_overlays -.->|"uses"| node_engines
node_render -->|"produces"| node_final
node_final -->|"inspected at cuts"| node_evaluation
node_evaluation -->|"requests views"| node_timeline
node_agent -->|"reviews output"| node_evaluation
node_evaluation -->|"issues prompt fixes"| node_edl
node_agent -->|"persists session"| node_memory
node_final -->|"delivers"| node_user

click node_skill "https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md"
click node_inventory "https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md"
click node_approval "https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md"
click node_transcribe "https://github.com/mengtang1114-forks/video-use/blob/main/helpers/transcribe.py"
click node_batch "https://github.com/mengtang1114-forks/video-use/blob/main/helpers/transcribe_batch.py"
click node_packing "https://github.com/mengtang1114-forks/video-use/blob/main/helpers/pack_transcripts.py"
click node_timeline "https://github.com/mengtang1114-forks/video-use/blob/main/helpers/timeline_view.py"
click node_render "https://github.com/mengtang1114-forks/video-use/blob/main/helpers/render.py"
click node_grade "https://github.com/mengtang1114-forks/video-use/blob/main/helpers/grade.py"
click node_overlays "https://github.com/mengtang1114-forks/video-use/tree/main/skills/manim-video"
click node_evaluation "https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_skill,node_inventory,node_approval,node_edl,node_memory,node_evaluation,node_final toneBlue
class node_transcribe,node_batch,node_transcripts,node_packing,node_packed,node_timeline toneAmber
class node_render,node_grade,node_overlays toneMint
class node_scribe,node_ffmpeg,node_engines toneRose
class node_user,node_agent,node_footage toneIndigo
```

## Components

### Editing workflow

- [Editing rules](https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md): `SKILL.md`
- [Inventory and strategy](https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md): `SKILL.md`
- [Strategy approval](https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md): `SKILL.md`
- **Edit decision list**
- **Project memory**
- [Cut evaluation](https://github.com/mengtang1114-forks/video-use/blob/main/SKILL.md): `SKILL.md`
- **Final video**

### Speech and review

- [Transcription](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/transcribe.py): `helpers/transcribe.py`
- [Batch transcription](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/transcribe_batch.py): `helpers/transcribe_batch.py`
- **Word transcripts**
- [Transcript packing](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/pack_transcripts.py): `helpers/pack_transcripts.py`
- **Packed transcript**
- [Visual drill-down](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/timeline_view.py): `helpers/timeline_view.py`

### Render and polish

- [Video rendering](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/render.py): `helpers/render.py`
- [Color grading](https://github.com/mengtang1114-forks/video-use/blob/main/helpers/grade.py): `helpers/grade.py`
- [Animation overlays](https://github.com/mengtang1114-forks/video-use/tree/main/skills/manim-video): `skills/manim-video`

### External integrations

- **ElevenLabs Scribe**
- **FFmpeg tools**
- **Overlay engines**

### Other components

- **Editor**
- **Editing agent**
- **Source footage**

## Connections

- Editor → Source footage: supplies
- Editor → Editing agent: requests edit
- Editing agent → Editing rules: follows
- Editing agent → Inventory and strategy: inspects
- Source footage → Inventory and strategy: inventoried by
- Editing agent → Strategy approval: proposes strategy
- Editor → Strategy approval: approves
- Source footage → Batch transcription: transcribed from
- Source footage → Transcription: transcribed from
- Batch transcription → Transcription: dispatches
- Transcription → FFmpeg tools: extracts audio
- Transcription → ElevenLabs Scribe: uploads audio
- Transcription → Word transcripts: writes
- Word transcripts → Transcript packing: reads
- Transcript packing → Packed transcript: writes
- Editing agent → Packed transcript: reads
- Editing agent → Visual drill-down: requests view
- Source footage → Visual drill-down: frames and audio
- Word transcripts → Visual drill-down: labels view
- Editing agent → Edit decision list: authors
- Edit decision list → Video rendering: drives render
- Video rendering → FFmpeg tools: invokes
- Video rendering → Color grading: applies grading
- Video rendering → Animation overlays: composites
- Animation overlays → Overlay engines: uses
- Video rendering → Final video: produces
- Final video → Cut evaluation: inspected at cuts
- Cut evaluation → Visual drill-down: requests views
- Editing agent → Cut evaluation: reviews output
- Cut evaluation → Edit decision list: issues prompt fixes
- Editing agent → Project memory: persists session
- Final video → Editor: delivers