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.
61
53%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 clearly defines a narrow, specific domain (Vertex AI ADK Terraform provisioning), provides explicit trigger phrases, and lists concrete infrastructure components being provisioned. The only minor note is the slightly awkward opening 'Execute use when' which could be smoother, but it does not materially impact functionality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and components: 'Provisions Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and secure multi-agent infrastructure.' These are highly specific, named resources. | 3 / 3 |
Completeness | Clearly answers both 'what' (provisions Agent Engine runtime, sandbox, Memory Bank, VPC Service Controls, IAM roles, multi-agent infrastructure) and 'when' (explicit trigger phrases and 'use when provisioning Vertex AI ADK infrastructure with Terraform'). | 3 / 3 |
Trigger Term Quality | Includes multiple natural trigger phrases users would say: 'deploy ADK terraform', 'agent engine infrastructure', 'provision ADK agent', 'vertex AI agent terraform', 'code execution sandbox terraform'. These cover realistic variations of how users would request this task. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Vertex AI ADK, Terraform, and specific infrastructure components like Agent Engine and code execution sandbox. Very unlikely to conflict with other skills due to the specificity of the domain. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a table of contents with no substantive content. It provides no executable Terraform code, no specific resource configurations, no concrete commands, and defers all meaningful content to reference files that don't exist in the bundle. For a complex infrastructure provisioning task, the complete absence of validation checkpoints, specific commands (like terraform plan/apply), and actual HCL code makes this skill non-functional.
Suggestions
Add concrete, executable Terraform HCL snippets for core resources (Agent Engine, IAM service accounts, VPC) directly in the skill body as a quick-start section.
Include specific terraform commands with validation checkpoints: 'terraform init', 'terraform plan -out=tfplan', review plan output, 'terraform apply tfplan', then post-deploy verification commands.
Either provide the referenced bundle files (implementation.md, errors.md, examples.md) or inline the critical content—currently the skill is an empty shell.
Remove the prerequisites section (Claude knows what Terraform and gcloud are) and replace with a lean variables/inputs specification showing required tfvars with example values.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with unnecessary context Claude already knows (prerequisites like 'Terraform 1.0+ installed', 'gcloud CLI authenticated'), explains obvious concepts, and the instructions are vague high-level descriptions rather than lean, actionable content. The overview restates the description verbosely. | 1 / 3 |
Actionability | No concrete code, no executable Terraform snippets, no specific commands, no copy-paste ready examples. The instructions are entirely abstract descriptions ('Configure Variables', 'Provision VPC', 'Deploy Agent Engine') with zero implementation detail. All concrete guidance is deferred to reference files that don't exist in the bundle. | 1 / 3 |
Workflow Clarity | While steps are numbered, they lack any specificity, validation checkpoints, or feedback loops. For infrastructure provisioning (a destructive/complex operation), there are no explicit validation commands, no 'terraform plan' before 'terraform apply', no error recovery guidance inline. The validate step at the end is vague ('Test agent endpoint and verify all components'). | 1 / 3 |
Progressive Disclosure | The skill references external files (implementation.md, errors.md, examples.md) which is good structure in principle, but no bundle files exist to back these references. The main file itself contains almost no substantive content—it's an empty shell pointing to nonexistent files, making the progressive disclosure structure hollow rather than functional. | 2 / 3 |
Total | 5 / 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
3a2d27d
- 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.