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

87%

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%

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 with executable commands and clear error-recovery guidance. The main weakness is mild redundancy between the 'When to Use', 'Quick Reference', and 'Typical Agent Workflow' sections.

Suggestions

Consolidate the command examples that overlap between 'Quick Reference' and 'Typical Agent Workflow' so each appears once, or have the workflow section reference the quick-reference block.

Trim the 'When to Use This Skill' list since the same triggers already appear in the frontmatter description, keeping only any novel use cases.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but 'When to Use This Skill' duplicates the frontmatter triggers and command examples recur across 'Quick Reference' and 'Typical Agent Workflow', so it could be tightened — matching anchor 2 rather than the fully lean anchor 3.	2 / 3
Actionability	Fully executable, copy-paste-ready `uv run $SCRIPT ...` commands with specific flags and a concrete troubleshooting table mapping symptoms to fixes, matching anchor 3.	3 / 3
Workflow Clarity	This is a single-action skill (call ask.py with a prompt) that is unambiguous, with a `--ping` sanity-check checkpoint and a troubleshooting table for error recovery; the simple-skill note allows a 3 here.	3 / 3
Progressive Disclosure	Content is organized into clear sections and points to a single one-level-deep bundle file (scripts/ask.py) that is real and clearly signaled, with no nested references.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 strong, specific description with explicit 'Use when' triggers and natural trigger phrases. The only weakness is second-person phrasing ('Use when you need to'), which the rubric penalizes on specificity.

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'), matching the anchor 3 example, but the description uses second person ('Use when you need to'), which the rubric penalizes by reducing specificity by one point.	2 / 3
Completeness	Clearly states what ('Query images with a local Ollama vision model without loading the image into the main agent context') and when ('Use when you need to describe a screenshot...') with an explicit 'Use when' clause, matching anchor 3.	3 / 3
Trigger Term Quality	Explicit trigger phrases users would naturally say ('describe image', 'what does this screenshot show', 'look at this image', 'vision query') give good coverage of natural terms, matching anchor 3.	3 / 3
Distinctiveness Conflict Risk	The niche is precise (local Ollama vision model, no main-context vision tokens, Gemma 4 only) with distinct triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 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: 2e0d276

Reviewed: 3 days 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.