Analyze images, extract text, and describe visual content using vision models through Crazyrouter.
Agent Execution:
SKILL_DIR = this SKILL.md file's directory${SKILL_DIR}/scripts/main.mjs[ -n "${CRAZYROUTER_API_KEY}" ] && echo "key_present" || echo "not_set"
| Result | Action |
|---|---|
| -------- | -------- |
key_present | Continue |
not_set | Ask user to set CRAZYROUTER_API_KEY. Get key at https://crazyrouter.com |
# Describe image
node ${SKILL_DIR}/scripts/main.mjs --image photo.jpg --prompt "Describe this image"
# Extract text (OCR)
node ${SKILL_DIR}/scripts/main.mjs --image receipt.png --prompt "Extract all text from this image"
# Analyze screenshot
node ${SKILL_DIR}/scripts/main.mjs --image screenshot.png --prompt "What errors are shown in this screenshot?"
# Use specific model
node ${SKILL_DIR}/scripts/main.mjs --image chart.png --prompt "Analyze this chart" --model gemini-2.5-flash
# Save output
node ${SKILL_DIR}/scripts/main.mjs --image document.jpg --prompt "Extract text" --output text.md
| Option | Description | Default |
|---|---|---|
| -------- | ------------- | --------- |
--image | Image file (required) | — |
--prompt | What to do with the image | Describe this image in detail |
--model | Vision model | gpt-4o |
--output | Save to file | stdout |
共 1 个版本