vision

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".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body for a single-purpose task: executable commands, a meaningful health-check checkpoint, and a compact troubleshooting table. Minor redundancy across sections is the only thing holding it back from a perfect content score.

Suggestions

Consolidate the repeated --info/--memory/--storage invocations and the model-selection explanation into one section to tighten token efficiency.

Promote the `--ping` health check to an explicit numbered validation step inside 'Typical Agent Workflow' so the checkpoint is unambiguous.

Dimension	Reasoning	Score
Conciseness	Largely lean with quick-reference commands and a compact troubleshooting table, but a few restatements (--info/--memory/--storage appear in both Quick Reference and System Info; model selection explained twice) keep it just below the fully lean anchor.	4 / 5
Actionability	Copy-paste-ready `uv run` commands with concrete example prompts, prerequisite install commands, and a symptom/cause/fix troubleshooting table fully cover the common cases.	5 / 5
Workflow Clarity	A clear three-step Typical Agent Workflow pairs with a `--ping` sanity check and a fail-fast + troubleshooting feedback loop, but validation is not an explicit numbered checkpoint within the workflow sequence.	4 / 5
Progressive Disclosure	Clean sectioned overview pointing to a single real referenced script (ask.py) with no nested references; appropriate for a simple single-purpose skill.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A model description: it concisely states what the skill does, when to use it with concrete triggers, prerequisites, and the script path, all in third person. No fluff, no over-claims, comprehensive action and trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'describe a screenshot, check whether rendered content is present, detect overlapping elements, or ask any visual question' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly states what ('Query images with a local Ollama vision model…'), when ('Use when you need to describe a screenshot…'), and lists concrete trigger phrases, satisfying the highest anchor.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases ('describe image', 'what does this screenshot show', 'check screenshot visually') plus file extensions (PNG/JPEG/WebP), matching the full-synonym-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (local Ollama vision querying scoped to Gemma 4) with distinct triggers and prerequisites, minimizing overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gridaco/grida
Path: .agents/skills/vision/SKILL.md
Commit: 8ef5e53

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.