vertex-agent-builder

Build and deploy production-ready generative AI agents using Vertex AI, Gemini models, and Google Cloud infrastructure with RAG, function calling, and multi-modal capabilities. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

45%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/jeremy-vertex-ai/skills/vertex-agent-builder/SKILL.md

Quality

Discovery

17%

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 has a critical flaw: the 'Use when' and 'Trigger' clauses are empty placeholders that provide no actual guidance for skill selection. While it names specific Google Cloud technologies, the lack of concrete actions and meaningful trigger terms makes it nearly useless for Claude to determine when to select this skill over others.

Suggestions

Replace placeholder text with explicit trigger phrases like 'Use when user mentions Vertex AI, Google Cloud AI, Gemini API, or building AI agents on GCP'

Add concrete actions such as 'Configure Vertex AI pipelines, implement RAG with Cloud Storage, deploy agents to Cloud Run'

Include natural user phrases like 'Google AI', 'GCP machine learning', 'Gemini integration', 'vector search on Google Cloud'

Dimension	Reasoning	Score
Specificity	Names the domain (Vertex AI, Gemini, Google Cloud) and lists some capabilities (RAG, function calling, multi-modal), but 'production-ready generative AI agents' is somewhat vague and doesn't describe concrete actions like 'deploy', 'configure', or 'integrate'.	2 / 3
Completeness	'Use when appropriate context detected' and 'Trigger with relevant phrases based on skill purpose' are meaningless placeholders that fail to answer 'when' at all. The 'what' is partially addressed but the 'when' is completely absent.	1 / 3
Trigger Term Quality	The phrase 'Trigger with relevant phrases based on skill purpose' is a placeholder that provides zero actual trigger terms. Technical terms like 'Vertex AI' and 'RAG' are present but common user phrases are missing entirely.	1 / 3
Distinctiveness Conflict Risk	The Google Cloud/Vertex AI/Gemini focus provides some distinctiveness from generic AI skills, but 'generative AI agents' and 'multi-modal capabilities' could overlap with many other AI-related skills.	2 / 3
	Total	6 / 12 Passed

Implementation

72%

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

This skill is well-structured and concise, effectively communicating the scope and workflow for building Vertex AI agents without unnecessary verbosity. However, it lacks concrete executable examples (deployment commands, actual code snippets, configuration files) that would make it immediately actionable. The workflow could benefit from explicit validation checkpoints with specific commands.

Suggestions

Add concrete deployment command examples (e.g., `gcloud ai agents deploy ...` or equivalent SDK code) in the Deploy step

Include at least one executable code snippet showing agent initialization or tool/function interface definition

Add explicit validation commands in the workflow (e.g., 'Run `gcloud ai agents describe ...` to verify deployment status; if failed, check logs with `gcloud logging read ...`')

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, avoiding explanations of concepts Claude already knows (like what Vertex AI or RAG is). Every section adds actionable value without padding or unnecessary context.	3 / 3
Actionability	The skill provides clear high-level guidance and structured workflows, but lacks executable code examples. The instructions describe what to do rather than showing concrete commands or copy-paste ready code snippets for deployment or configuration.	2 / 3
Workflow Clarity	Steps are clearly sequenced in the Instructions section, but validation checkpoints are implicit rather than explicit. The 'evaluation' step mentions checks but doesn't provide a concrete validate-fix-retry feedback loop for deployment failures.	2 / 3
Progressive Disclosure	Excellent structure with a clear overview, well-organized sections, and appropriate references to external resources (full guide, repo standards, official docs). References are one level deep and clearly signaled.	3 / 3
	Total	10 / 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: 227604c

Reviewed: 2 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.