adk-infra-expert

Name: adk-infra-expert
Rating: 67 (1 reviews)
Author: jeremylongshore

tessl install github:jeremylongshore/claude-code-plugins-plus-skills --skill adk-infra-expert

github.com/jeremylongshore/claude-code-plugins-plus-skills

Execute use when provisioning Vertex AI ADK infrastructure with Terraform. Trigger with phrases like "deploy ADK terraform", "agent engine infrastructure", "provision ADK agent", "vertex AI agent terraform", or "code execution sandbox terraform". Provisions Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and secure multi-agent infrastructure.

Review Score

67%

Validation Score

13/16

Implementation Score

35%

Activation Score

100%

SKILL.md

Review

Evals

Generated

11 days ago

Warnings & errors only

Criteria	Score
allowed_tools_field	'allowed-tools' contains unusual tool name(s)
metadata_version	'metadata' field is not a dictionary
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata

Overall Assessment

This skill provides a reasonable structural outline for ADK infrastructure provisioning but fails to deliver actionable content. The instructions are abstract descriptions rather than executable Terraform code or specific gcloud commands. The empty Output section and reliance on external references without providing core quick-start content significantly reduces its utility.

Suggestions

Add concrete Terraform HCL code blocks for each major step (VPC, IAM, Agent Engine configuration) that are copy-paste ready
Include specific gcloud and terraform CLI commands with example variable values (e.g., `terraform init -backend-config=...`)
Add validation commands after critical steps (e.g., `gcloud ai agent-engines describe` to verify deployment, terraform plan output checks)
Populate the Output section with expected terraform output values or deployment verification criteria

Dimension	Score	Reasoning
Conciseness	2/3	The content is reasonably efficient but includes some unnecessary padding like the verbose overview and prerequisites that Claude would already understand. The instructions section is lean but lacks substance.
Actionability	1/3	The skill provides only vague, abstract steps with no concrete Terraform code, commands, or executable examples. Instructions like 'Configure Variables' and 'Provision VPC' describe rather than instruct with specific HCL or CLI commands.
Workflow Clarity	2/3	Steps are listed in sequence but lack validation checkpoints between critical operations. No feedback loops for error recovery, and 'Validate Deployment' is too vague without specific verification commands or expected outputs.
Progressive Disclosure	2/3	References to external files (errors.md, examples.md) are present, but the Output section is empty and the main content lacks the quick-start substance that should precede references. The structure exists but content is missing.

Overall Assessment

This is a strong skill description that excels across all dimensions. It provides specific infrastructure components being provisioned, includes comprehensive trigger phrases users would naturally use, explicitly states when to use it, and has a clear distinctive niche combining Vertex AI ADK with Terraform infrastructure provisioning.

Dimension	Score	Reasoning
Specificity	3/3	Lists multiple specific concrete actions: 'Provisions Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and secure multi-agent infrastructure.' These are detailed, concrete infrastructure components.
Completeness	3/3	Clearly answers both what (provisions specific infrastructure components) and when (explicit 'Use when' clause with 'Trigger with phrases like...' providing clear activation guidance).
Trigger Term Quality	3/3	Excellent coverage of natural trigger phrases: 'deploy ADK terraform', 'agent engine infrastructure', 'provision ADK agent', 'vertex AI agent terraform', 'code execution sandbox terraform'. These are terms users would naturally say when needing this skill.
Distinctiveness Conflict Risk	3/3	Highly distinctive with specific niche: Vertex AI ADK + Terraform combination with unique components like 'Agent Engine runtime', '14-day code execution sandbox', and 'Memory Bank'. Unlikely to conflict with generic Terraform or cloud skills.