Setup & Installation
openclaw skills install @miladnoo/nvidia-kimi-vision
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install nvidia-kimi-vision
Version History
v1.0.3Feb 18, 2026 - Version note by skill developer:
Republished
What This Skill Does
Analyzes images using the Kimi K2.5 multimodal model via NVIDIA NIM API. Useful for adding vision capabilities to agents or models that lack native image understanding. Supports PNG, JPG, JPEG, and WebP formats.
Gives any agent or model image understanding without requiring a native vision model, using NVIDIA NIM's free tier for fast inference.
When to use it
- Extract text from a screenshot
- Describe what's in a photo
- Analyze a meme or diagram
- Identify objects in an image
- Add vision to a non-vision LLM workflow
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: What does this receipt say?
AGENT
- 1Receives the image path and prompt from the user
- 2Checks for an NVIDIA NIM API key in ~/.config/nvidia-kimi-api-key
- 3Calls the Kimi K2.5 model via NVIDIA NIM API with the image and prompt
- 4Returns the extracted text from the receipt
OUTPUT
Itemized list of purchases and totals read from the receipt image
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
NVIDIA NIM API key from build.nvidia.com (free tier available)