菜单
Analyze local images using OpenRouter vision models. Use when the user question depends on visual content from a local image file — visual question answering, describing images, reading text in images, identifying objects, etc.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Search Google via SerpAPI (Google Search, Google News, Google Local). Use when you need to search the web, find news articles, or look up local businesses. Supports country/language targeting for region-specific results.
基于 SOC 职业分类
| name | image-analysis |
| description | Analyze local images using OpenRouter vision models. Use when the user question depends on visual content from a local image file — visual question answering, describing images, reading text in images, identifying objects, etc. |
| metadata | {"requires":{"bins":["python3"],"env":["OPENROUTER_API_KEY"]}} |
Analyze local images with OpenRouter multimodal chat completions.
# Analyze an image with a question
python3 {baseDir}/scripts/analyze_image.py --image "/path/to/image.png" --prompt "Describe what you see in the image"
# Use a specific model
python3 {baseDir}/scripts/analyze_image.py --image "/path/to/photo.jpg" --prompt "What text is visible?" --model "google/gemini-2.0-flash-001"
# Increase output length and timeout
python3 {baseDir}/scripts/analyze_image.py --image "/path/to/diagram.png" --prompt "Explain this diagram" --max-tokens 4096 --timeout 120
| Flag | Description | Default |
|---|---|---|
--image | Path to local image file (required) | — |
--prompt | Question or instruction for the image (required) | — |
--model | Override model id | env-configured |
--max-tokens | Max output tokens | 2048 |
--timeout | HTTP timeout in seconds | 60 |
Model is resolved in this order:
--model argumentOPENROUTER_VISION_MODEL env varOPENROUTER_MODEL env varSet OPENROUTER_API_KEY env var. Optionally configure OPENROUTER_BASE_URL, OPENROUTER_PROVIDER_ORDER, and OPENROUTER_ALLOW_FALLBACKS.
PNG, JPEG, GIF, WebP, BMP, and other common image formats.