bradautomates/claude-video
Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.
What is bradautomates/claude-video?
bradautomates/claude-video is a repository whose own project materials describe it as Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude. Codex, Cursor, Copilot, Gemini CLI, or any of 50+ Agent Skills hosts: -g installs globally for your user, available across all projects. This Graphify demo keeps bradautomates/claude-video as the primary keyword while adding source-derived context, README signals, and an interactive code graph for deeper exploration.
Source: README.md at 83da59fa78c3
Graphify architecture insights for bradautomates/claude-video
bradautomates/claude-video has a compact Graphify map with 256 nodes, 445 edges, and 17 communities. The graph turns bradautomates/claude-video into an architecture map: dense communities point to related implementation areas, while high-degree nodes from the Graphify report are good starting points for code review, onboarding, and dependency exploration.
README-derived project notes
- bradautomates/claude-video is described by its project source as: Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude. Codex, Cursor, Copilot, Gemini CLI, or any of 50+ Agent Skills hosts: -g installs globally for your user, available across all projects
- The project README exposes reader-facing sections such as What people actually use it for, How it works, Frame budget why it matters, and Frame deduplication, which helps explain how bradautomates/claude-video is positioned and used
- bradautomates/claude-video was captured from the repository at commit 83da59fa78c3 and analyzed in code-only mode, so this page connects project documentation with the generated code graph
- bradautomates/claude-video is primarily a Python project, which makes the graph useful for understanding important files, modules, and dependency relationships before opening the source tree
Related code graphs
- junegunn/fzf — Go, 1,813 nodes
- wonderwhy-er/DesktopCommanderMCP — TypeScript, 1,985 nodes
- unclecode/crawl4ai — Python, 10,340 nodes
- usestrix/strix — Python, 1,325 nodes
Graphify report highlights
Summary
- 256 nodes · 445 edges · 17 communities (14 shown, 3 thin omitted)
- Extraction: 95% EXTRACTED · 5% INFERRED · 0% AMBIGUOUS · INFERRED: 21 edges (avg confidence: 0.8)
- Token cost: 0 input · 0 output
God nodes
- main() - 21 edges
- _run() - 12 edges
- extract_keyframes() - 10 edges
- transcribe_video() - 10 edges
- cmd_install() - 9 edges
- extract_scene_or_uniform() - 8 edges
Surprising connections
- _status() --calls--> get_config() [INFERRED]
- main() --calls--> frame_cap() [INFERRED]
- main() --calls--> is_url() [INFERRED]
- main() --calls--> fetch_captions() [INFERRED]
FAQ about bradautomates/claude-video
What is bradautomates/claude-video?
bradautomates/claude-video is described by its repository as Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude. Codex, Cursor, Copilot, Gemini CLI, or any of 50+ Agent Skills hosts: -g installs globally for your user, available across all projects. This page adds a Graphify code graph so readers can inspect how the project is structured.
What does the bradautomates/claude-video Graphify graph show?
bradautomates/claude-video has a compact Graphify map with 256 nodes, 445 edges, and 17 communities. It highlights communities, important nodes, and relationships extracted from the captured source commit.
Why use Graphify to explore bradautomates/claude-video?
Graphify gives bradautomates/claude-video a visual architecture layer, making it easier to find central files, understand module boundaries, and decide where to start reading the code.
Where did the bradautomates/claude-video page content come from?
The project notes are derived from README.md at 83da59fa78c3, repository metadata, and the Graphify report generated for the captured commit.