vertex-ai-media-master

Execute automatic activation for all google vertex ai multimodal operations operations. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

21%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/productivity/003-jeremy-vertex-ai-media-master/skills/vertex-ai-media-master/SKILL.md

Quality

Discovery

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

This description is almost entirely composed of placeholder language and meta-instructions rather than actual content. It fails to specify what concrete actions the skill performs, provides no real trigger terms a user would naturally use, and offers no meaningful guidance for when Claude should select this skill. It reads like a template that was never filled in.

Suggestions

Replace vague 'multimodal operations' with specific actions like 'Analyze images, generate text from visual inputs, process video content, and transcribe audio using Google Vertex AI'.

Add a concrete 'Use when...' clause with natural trigger terms such as 'Use when the user asks about Vertex AI, Google Cloud AI, image analysis, multimodal prompts, or Gemini model integration'.

Remove meta-language like 'Execute automatic activation' and 'Trigger with relevant phrases based on skill purpose'—these are instructions about the description, not the description itself.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'automatic activation' and 'multimodal operations operations' without listing any concrete actions. No specific capabilities (e.g., image analysis, video processing, text generation) are mentioned.	1 / 3
Completeness	The 'what' is essentially absent—'multimodal operations' is not a meaningful description of capabilities. The 'when' clause ('when appropriate context detected') is a vacuous placeholder that provides zero guidance on actual trigger conditions.	1 / 3
Trigger Term Quality	The description contains no natural keywords a user would actually say. 'Appropriate context detected' and 'relevant phrases based on skill purpose' are meta-placeholders, not real trigger terms. 'Google Vertex AI' is the only semi-useful term but lacks any user-facing variations.	1 / 3
Distinctiveness Conflict Risk	The mention of 'Google Vertex AI' provides some domain specificity that distinguishes it from generic skills, but the rest of the description is so vague that it could overlap with any AI/ML-related skill.	2 / 3
	Total	5 / 12 Passed

Implementation

35%

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

This skill provides a broad overview of Vertex AI multimodal operations but critically lacks executable code examples, making it largely descriptive rather than actionable. The error handling table and structured sections show good organizational intent, but the absence of concrete Python snippets, API call patterns, or copy-paste-ready commands significantly limits its utility. The referenced bundle file for detailed capabilities doesn't exist, leaving the skill without the depth needed for complex multi-model orchestration.

Suggestions

Add executable Python code examples for at least the core operations (video analysis with Gemini, image generation with Imagen 4, audio with Lyria) including actual API calls, parameter construction, and response handling.

Replace the vague step 7 validation instruction with concrete validation code or commands, such as checking response status codes, verifying file sizes/formats, or validating JSON output against a schema.

Create the referenced `references/core-capabilities.md` bundle file with detailed model-specific code patterns, or remove the reference if it doesn't exist.

Convert the narrative examples into executable code blocks showing the actual API calls, request construction, and response parsing for each scenario.

Dimension	Reasoning	Score
Conciseness	The skill is moderately verbose with some unnecessary explanation (e.g., the Output section lists things Claude could infer, and the Examples section describes workflows at a high level without executable code). The prerequisites and error handling table are useful but the overall content could be tightened.	2 / 3
Actionability	Despite covering multiple complex operations, the skill provides zero executable code. All instructions are abstract descriptions ('Initialize the Vertex AI client', 'Construct the generation request') with no concrete Python snippets, API calls, or copy-paste-ready commands. The examples describe inputs/outputs narratively rather than showing actual code.	1 / 3
Workflow Clarity	Steps are listed in a logical sequence and the error handling table is a useful addition, but validation is mentioned only vaguely in step 7 ('Validate results against brand guidelines or schema expectations') with no concrete validation commands or feedback loops for error recovery.	2 / 3
Progressive Disclosure	The skill references a bundle file (`${CLAUDE_SKILL_DIR}/references/core-capabilities.md`) and external documentation links, which is good structure. However, no bundle files were actually provided, and the main SKILL.md contains a lot of inline content (full error table, detailed examples) that could be better organized into separate reference files.	2 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 6e9558f

Reviewed: 4 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.