Capture photos remotely from mobile devices for hardware inspection, PCB debugging, chip identification, document capture, or visual analysis. Use when you need to see something in the physical world - circuit boards, chip markings, component labels, error screens, handwritten notes, or any physical object the user mentions.
Capture photos from your mobile device for hardware debugging, chip identification, or visual analysis. Use when you need to see physical objects like circuit boards, error screens, or handwritten notes that the user mentions.
/plugin marketplace add aimoda/claude-code-remote-camera-plugin/plugin install remote-camera@aimodaThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Capture and analyze photos from the user's mobile device to help with hardware debugging, visual inspection, documentation, and troubleshooting tasks.
Use remote camera capture when:
The user will mention phrases like "take a photo", "can you see this", "look at this chip", "what's this component", or describe something physical they want help with.
The workflow uses two MCP tools: generate_upload_url and poll_for_upload.
Call the generate_upload_url tool with a clear message parameter that tells the user what to photograph:
{
"message": "Take a photo of the chip markings on the main IC"
}
This returns:
capture_url: A URL for the user to open on their mobile devicesession_id: An identifier for this capture sessionShow the capture URL to the user in a clear, actionable way:
I've generated a remote camera capture link for you. Please open this URL on your mobile device to take the photo:
[capture_url]
Instructions: [repeat the message you provided]
The URL will open a camera interface where you can capture the photo. Once you've taken the photo, I'll automatically detect when it's uploaded.
Immediately after presenting the URL, call poll_for_upload with the session_id:
{
"session_id": "[session_id from step 1]",
"timeout": 120
}
This will wait up to 120 seconds (2 minutes) for the user to capture and upload the photo. The tool provides progress updates while waiting.
When the upload completes, you'll receive:
download_url: A presigned URL to download the captured photoetag: A unique identifier for this specific uploadlast_modified: Timestamp of when the photo was uploadedUse the Read tool to fetch and analyze the downloaded photo:
Read the image at [download_url]
Then provide your analysis based on what the user asked for - identify chips, explain circuit layouts, read error messages, transcribe handwritten notes, etc.
The same capture URL can be reused multiple times! If the user needs to take additional photos:
not_etag parameter with the previous photo's etag to detect the new upload:{
"session_id": "[same session_id]",
"timeout": 120,
"not_etag": "[etag from previous upload]"
}
This allows efficient multi-photo workflows without generating new URLs each time.
Good capture instructions are specific and actionable:
Good examples:
Less effective:
Include:
When presenting capture URLs, you can include these tips for better photos:
"I need to identify this chip on my board."
"This circuit isn't working, can you help debug it?"
"My device is showing an error but I can't copy the text."
"Can you help me understand this schematic?"
If the poll times out:
If you can't analyze the photo:
remote-camera-mcp/{session_id}This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.