multimodal-looker

Image and video analysis specialist

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/multimodal-looker/SKILL.md

Quality

Content

60%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.

The body is a clear, well-organized overview for a simple visual-analysis skill with useful output templates, but it leans on demonstrative examples and persona/quote padding rather than crisp executable guidance. Tightening the framing and adding explicit instructions on how to perform each analysis would lift it from good to strong.

Suggestions

Remove the closing motivational quote and the redundant persona restatement to tighten token efficiency.

Convert each use-case example from a pure output sample into an actionable instruction, e.g. 'For a UI screenshot, report: layout, header/sidebar/main regions, colors (hex), typography, WCAG issues, and ranked recommendations'.

Add a brief note on which analysis format to select based on input type (screenshot vs diagram vs error) so Claude knows when to apply each template.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — a capabilities list, three compact use-case templates, and an integration list — but includes non-earning tokens such as the 'You are Multimodal Looker' persona line and the closing motivational quote, and could be tightened. This matches the score-3 anchor 'Mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Each use case provides a concrete output template (layout/color/issue breakdown, layered architecture description, error-cause-solution format) which is useful for an analysis skill, but these are demonstrations of expected output rather than executable instructions on how to perform the analysis, matching 'Some concrete guidance but incomplete; pseudocode instead of executable code; missing key details'.	3 / 5
Workflow Clarity	This is a single-purpose analysis skill with no destructive or batch operation requiring validation, so the simple-skill exception applies; the single action is unambiguous and well-organized into capabilities and use-case examples, fitting 'Clear sequence with most checkpoints present; minor validation gaps' adapted to a simple skill.	4 / 5
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ absent) and none are needed; content is organized into clear sections (Capabilities, Use Cases, Integration) with no nested references, aligning with the score-4 anchor 'Good structure; most content is appropriately placed'. It stops short of 5 because the three inlined use-case examples could arguably live in separate reference files and slightly pad the overview.	4 / 5
	Total	14 / 20 Passed

Description

48%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.

The description is concise and clearly identifies the visual-analysis niche, but it is too terse to be a strong trigger description: it lacks concrete actions and any explicit 'Use when' guidance. Raising specificity and adding trigger phrases would move it from adequate to strong.

Suggestions

Add 2-3 concrete actions, e.g. 'describes images, extracts text via OCR, interprets diagrams and screenshots, and analyzes video frames'.

Append a 'Use when...' clause with natural trigger phrases users actually say, e.g. 'Use when the user shares a screenshot, asks to describe or read text from an image, or wants video frame analysis'.

Include common synonyms/extensions (screenshot, diagram, OCR, frame) to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Image and video analysis specialist' names the domain (image and video) but the only action word 'analysis' is generic and 'specialist' is a role, not a concrete action — matching the score-2 anchor 'Names the domain but actions are minimal or generic'. It does not reach score 3 because no specific concrete actions (e.g. OCR, captioning, frame extraction) are listed.	2 / 5
Completeness	It states a clear 'what' (image and video analysis) but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric guideline a missing 'when' caps completeness at 3 — 'Has a clear what but when is missing or only weakly implied'.	3 / 5
Trigger Term Quality	'Image and video analysis' surfaces relevant natural keywords users would say, but it omits common variations and synonyms a user might actually use ('screenshot', 'diagram', 'frame', 'OCR', 'describe this picture'), matching the score-3 anchor of 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	'Image and video analysis specialist' carves out a mostly distinct visual/multimodal niche with only minor overlap risk against other media-related skills, aligning with the score-4 anchor 'Mostly distinct; minor overlap risk with closely related skills'.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TurnaboutHero/oh-my-antigravity
Path: skills/multimodal-looker/SKILL.md
Commit: f73e1ff

Reviewed: 15 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.