OpenSkillIndex← back to search
claude-codeopenclawresearch

Skills llava-vision

install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/447992399/llava-vision" ~/.claude/skills/openclaw-skills-llava-vision && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/447992399/llava-vision" ~/.openclaw/skills/openclaw-skills-llava-vision && rm -rf "$T"
manifest: skills/447992399/llava-vision/SKILL.md
tags
#image-recognition#llama#vision#local-llm#computer-vision#image-analysis
source content

LLaVA Vision Skill

This skill forwards an image to a locally running llama.cpp server that hosts a LLaVA model and returns the model’s text description of the image. It accepts either a local file path or a remote image URL.

Usage

clawhub llava-vision --image /path/to/photo.jpg
# or
clawhub llava-vision --image https://example.com/photo.jpg

The skill uses the built‑in vision_analyze tool, which expects an image file path. If the image cannot be read or the server is unreachable, an error message will be returned.

Dependencies

  • Node.js (the skill itself)
  • A local llama.cpp server with the LLaVA model exposed at the default endpoint.

Example

$ clawhub run llava-vision --image ./cat.png
The image contains a cat sitting on a windowsill, looking out at a sunny garden.