6 custom skills (assign-task, dispatch-webhook, daily-briefing, task-capture, qmd-brain, tts-voice) with technical documentation. Compatible with Claude Code, OpenClaw, Codex CLI, and OpenCode.
30 lines
1.2 KiB
Markdown
30 lines
1.2 KiB
Markdown
# Camera Capture Documentation
|
|
|
|
## Overview
|
|
|
|
OpenClaw enables camera functionality across multiple platforms through agent workflows. The feature supports photo capture (JPG) and video clips (MP4 with optional audio) on iOS, Android, and macOS devices.
|
|
|
|
## Key Features by Platform
|
|
|
|
**iOS & Android nodes** offer identical capabilities:
|
|
- Photo capture via `camera.snap` command
|
|
- Video recording via `camera.clip` command
|
|
- User-controlled settings (default enabled)
|
|
- Foreground-only operation
|
|
- Payload protection (base64 under 5 MB)
|
|
|
|
**macOS app** includes:
|
|
- Same camera commands as mobile platforms
|
|
- Camera disabled by default in settings
|
|
- Additional screen recording capability (separate from camera)
|
|
|
|
## Important Constraints
|
|
|
|
Video clips are capped (currently `<= 60s`) to avoid oversized node payloads. Photos are automatically recompressed to maintain payload limits.
|
|
|
|
Camera and microphone access require standard OS permission prompts. Android requires explicit runtime permissions for `CAMERA` and `RECORD_AUDIO` (when applicable).
|
|
|
|
## Usage
|
|
|
|
CLI helpers simplify media capture, automatically writing decoded files to temporary locations and printing `MEDIA:<path>` for agent integration.
|