Menu
Analyze images using vision models (GPT-4o or Claude Opus)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Execute a single agent step with custom system prompt and wait for completion.
Control the CARNELIAN browser control server (status/start/stop/tabs/snapshot/screenshot/navigate/act). Routes to the local browser control HTTP server.
Render canvas graphics and visualizations via Carnelian gateway node.invoke API
Communicate with Windsurf Cascade via JSONL channel files (message/delegate/request_help/share_context/status).
Manage Gateway cron jobs (status/list/add/update/remove/run/runs) and send wake events.
Send a message to a Discord channel via the Discord REST API
| name | image-analyze |
| description | Analyze images using vision models (GPT-4o or Claude Opus) |
| metadata | {"CARNELIAN":{"emoji":"🔬","requires":{"env":["OPENAI_API_KEY","ANTHROPIC_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"},"carnelian":{"runtime":"node","version":"1.0.0","sandbox":{"network":"full","resourceLimits":{"maxMemoryMB":128,"maxCpuPercent":25,"timeoutSecs":30},"env":{"OPENAI_API_KEY":"${OPENAI_API_KEY}","ANTHROPIC_API_KEY":"${ANTHROPIC_API_KEY}"}},"capabilities":["net.http"]}} |
Analyze images using vision models (GPT-4o or Claude Opus).
Ported from CARNELIAN image-tool.ts.
{
image: string; // Required: HTTP(S) URL or data: URL
prompt?: string; // Optional: analysis prompt (default "Describe the image.")
model?: string; // Optional: model to use (default based on provider)
provider?: "openai" | "anthropic"; // Optional: provider (default based on available API keys)
}
{
text: string; // Analysis result
model: string; // Model used
provider: string; // Provider used
}
openai if OPENAI_API_KEY is set, otherwise anthropicgpt-4o, gpt-4o-mini, gpt-4-turboclaude-opus-4-5, claude-sonnet-4, claude-3-5-sonnet-20241022{
"image": "https://example.com/photo.jpg",
"prompt": "What objects are in this image?",
"provider": "openai"
}