Vision

What it does

When your agent uses it

• You need to describe a screenshot
• Check whether rendered content is present
• Detect overlapping elements
• Ask any visual question about a PNG/JPEG/WebP file

Example prompts

• “describe image”
• “what does this screenshot show”
• “does the canvas contain content”
• “/vision”

Requirements

• Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1A tool (browser automation, screenshot capture, golden renderer) writes
2. 2Call ask.py with a targeted prompt suited to the task.
3. 3Parse the text response to decide the next action.

What it can do on your machine

Read from SKILL.md and the folder at commit 165496f. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • uv
  • ollama
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • ollama.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vision loads about 1.5k tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 478 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~153

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from gridaco/grida at commit 165496f, republished under its Apache-2.0 licence (© gridaco). 478 words, ~1,473 tokens.

name

vision

description

Query images with a local Ollama vision model without loading the image into the main agent context. Use when you need to describe a screenshot, check whether rendered content is present, detect overlapping elements, or ask any visual question about a PNG/JPEG/WebP file. Requires Ollama running locally with the Gemma 4 multimodal model (`gemma4` on Ollama). Script: .agents/skills/vision/scripts/ask.py. Trigger phrases: "describe image", "what does this screenshot show", "does the canvas contain content", "check screenshot visually", "look at this image", "any overlapping elements", "vision query".

SCRIPT=.agents/skills/vision/scripts/ask.py

# health check (fast, no image, confirms Ollama + model respond)
uv run $SCRIPT --ping

# system info — memory, storage, installed models
uv run $SCRIPT --info
uv run $SCRIPT --memory
uv run $SCRIPT --storage

# describe an image (default prompt)
uv run $SCRIPT path/to/image.png

# explicit shortcut
uv run $SCRIPT path/to/image.png describe

# custom question
uv run $SCRIPT path/to/image.png \
  --prompt "Do you see any overlapping UI elements?"

uv run $SCRIPT canvas.png \
  --prompt "Does this canvas contain any designed content, or is it empty?"

# optional: pin a specific Gemma 4 tag (default is any installed gemma4)
uv run $SCRIPT image.png --model gemma4:e4b

# list installed Gemma 4 vision models
uv run $SCRIPT --list-models

# start Ollama (if not already running)
ollama serve

# install Gemma 4 (multimodal — required for this skill)
ollama pull gemma4

uv run $SCRIPT --info      # memory + storage + model list
uv run $SCRIPT --memory    # just memory
uv run $SCRIPT --storage   # just storage

# Quick sanity check first
uv run $SCRIPT --ping

# Verify a browser screenshot has content before including it in a doc
uv run $SCRIPT /tmp/preview.png \
  --prompt "Answer with YES or NO: does this screenshot show any visible UI content, shapes, or text?"

# Describe a captured screenshot for a PR description
uv run $SCRIPT /tmp/canvas-screenshot.png \
  --prompt "Describe what visual effect is shown. Be specific about blur, colors, and shapes."

© gridaco, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in .agents/skills/vision of gridaco/grida.

• SKILL.md
• scripts/ask.py

Open the folder on GitHubat commit 165496f