CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/devops/jeremy-adk-terraform/skills/adk-infra-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-5

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

The body is well-organized and token-efficient, but it functions as an outline rather than an operating guide: no concrete commands or code, weak validation checkpoints for risky Terraform operations, and broken/incomplete navigation to most of the bundle files. Concrete execution detail exists in the bundle but the body fails to surface it.

Suggestions

Add executable anchors to the Instructions, e.g. 'terraform init' backed by scripts/init-terraform.sh, required variables with example values, and a 'terraform plan' review before apply, so the steps can actually be followed.

Insert explicit validation checkpoints between steps (e.g. verify VPC-SC perimeter before deploying Agent Engine) instead of a single vague 'Test agent endpoint' at the end.

Fix navigation to the bundle: link references/implementation.md explicitly, remove or create the nonexistent ${CLAUDE_SKILL_DIR}/examples/ path, and either reference or drop ARD.md and PRD.md from the bundle.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows, but the Overview paragraph largely duplicates the frontmatter description and 'See Terraform implementation details for output format specifications' is an unspecific sentence that could be trimmed or made a real link.

4 / 5

Actionability

All eight instructions are high-level hints ('Set up backend for remote state storage', 'Create network infrastructure with Private Service Connect') with no commands, code, or file paths; the bundled scripts/init-terraform.sh is never mentioned, so nothing in the body is directly executable.

2 / 5

Workflow Clarity

The eight steps are clearly sequenced and end with 'Validate Deployment', but validation is a single vague mention ('Test agent endpoint') with no per-step checkpoints and no terraform plan/validate gates for risky apply operations, leaving feedback loops implicit.

3 / 5

Progressive Disclosure

references/errors.md and references/examples.md are properly linked one level deep, but implementation.md is only vaguely referenced without a path, ARD.md, PRD.md, and scripts/init-terraform.sh are never referenced from the body, and the ${CLAUDE_SKILL_DIR}/examples/ path does not exist in the bundle.

3 / 5

Total

12

/

20

Passed

Description

87%Weight 40%Scale 1-5

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

A strong, distinctive description with explicit what/when coverage and concrete trigger phrases. Its weaknesses are the garbled opening phrase 'Execute use when', a trailing buzzword clause, and somewhat narrow trigger-term variation coverage.

DimensionReasoningScore

Specificity

The description lists several concrete components ('Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles'), but it relies on a single verb ('Provisions') and pads the list with the buzzword 'secure multi-agent infrastructure', so it falls just short of comprehensive concrete actions.

4 / 5

Completeness

It explicitly answers both 'what' ('Provisions Agent Engine runtime... Memory Bank, VPC Service Controls, IAM roles') and 'when' with concrete trigger phrases ('Trigger with phrases like...'), matching the top anchor despite the grammatically mangled opening 'Execute use when'.

5 / 5

Trigger Term Quality

It gives five explicit, natural trigger phrases ('deploy ADK terraform', 'agent engine infrastructure', 'provision ADK agent', 'vertex AI agent terraform', 'code execution sandbox terraform'), but misses common variations a user might say such as 'agent engine setup' or 'gcp agent infrastructure'.

4 / 5

Distinctiveness Conflict Risk

The Vertex AI ADK + Terraform provisioning niche is highly specific with distinct trigger vocabulary, making conflicts with other skills very unlikely.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository

jeremylongshore/tons-of-skills-marketplace

Path

plugins/devops/jeremy-adk-terraform/skills/adk-infra-expert/SKILL.md

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.