adk-infra-expert
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.
76
Quality
71%
Does it follow best practices?
Impact
84%
1.29xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/devops/jeremy-adk-terraform/skills/adk-infra-expert/SKILL.mdQuality
Discovery
100%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 is a strong skill description that excels across all dimensions. It provides specific infrastructure components being provisioned, includes natural trigger phrases users would actually say, clearly states both what the skill does and when to use it, and has a distinct enough niche (Vertex AI ADK + Terraform) to avoid conflicts with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | 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. | 3 / 3 |
Completeness | Clearly answers both what (provisions specific infrastructure components) and when ('Execute use when provisioning Vertex AI ADK infrastructure with Terraform' plus explicit trigger phrases). Has explicit 'Trigger with phrases like...' guidance. | 3 / 3 |
Trigger Term Quality | 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 realistic phrases users would say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific technology stack (Vertex AI ADK + Terraform) and unique components (Agent Engine, Memory Bank, VPC Service Controls). Unlikely to conflict with generic Terraform or cloud provisioning skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has good structural organization with appropriate progressive disclosure to reference files, but critically lacks actionable content. The main body reads like a table of contents rather than executable guidance - there's no Terraform code, no specific resource configurations, and no concrete commands. For infrastructure provisioning, the absence of validation checkpoints between steps is a significant gap.
Suggestions
Add concrete Terraform code examples for key resources (Agent Engine, VPC, IAM service accounts) directly in the skill or ensure the referenced implementation.md contains copy-paste ready HCL
Include specific CLI commands for each step (e.g., 'terraform init -backend-config=...', 'terraform plan -out=tfplan')
Add explicit validation checkpoints after critical steps: 'terraform plan' review before apply, 'terraform state list' verification, endpoint health checks
Remove or condense the Prerequisites section - Claude knows these basics; focus on project-specific requirements only
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary preamble in the overview and prerequisites that Claude would already know (e.g., explaining what Terraform is, basic setup requirements). The instructions section could be more direct. | 2 / 3 |
Actionability | The skill provides only high-level step descriptions without any concrete Terraform code, commands, or executable examples. Steps like 'Initialize Terraform' and 'Configure Variables' are vague directions rather than actionable instructions with specific HCL configurations or CLI commands. | 1 / 3 |
Workflow Clarity | Steps are listed in sequence but lack validation checkpoints between critical operations. For infrastructure provisioning (a potentially destructive operation), there should be explicit terraform plan validation, state verification, and rollback guidance rather than just 'Validate Deployment' at the end. | 2 / 3 |
Progressive Disclosure | Good structure with clear references to separate files for implementation details, errors, and examples. References are one level deep and well-signaled with descriptive links. The main skill serves as an appropriate overview. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
81%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 | |
- Commit
454476c
- Reviewed
Table of Contents
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.