CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gcp-cloud-architect

Design GCP architectures for startups and enterprises. Use when asked to design Google Cloud infrastructure, deploy to GKE or Cloud Run, configure BigQuery pipelines, optimize GCP costs, or migrate to GCP. Covers Cloud Run, GKE, Cloud Functions, Cloud SQL, BigQuery, and cost optimization.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A highly actionable skill with a well-sequenced 6-step workflow, verified script interfaces, explicit validation checkpoints, and error-recovery guidance. The main drag is redundancy — the Tools and Quick Start sections restate commands and patterns already covered in the workflow — and a long body that inlines template content the reference files already carry.

Suggestions

Trim the Tools section: replace the repeated command invocations with a one-line description per script (flags are already demonstrated in Steps 2-4), freeing tokens in the context window.

Consolidate the pattern lists: Step 2 and the Quick Start section both enumerate the four architecture patterns; keep one and link the other to references/architecture_patterns.md.

Move the full Terraform and cloudbuild.yaml templates into the references (architecture_patterns.md already contains per-pattern Terraform examples) and keep only a short excerpt inline, shortening the body toward a lean overview.

DimensionReasoningScore

Conciseness

No conceptual padding (nothing explains what GCP or Terraform is), but there is noticeable duplication: the Tools section repeats the exact commands already shown in Steps 2-4 (e.g., "python scripts/deployment_manager.py --app-name my-app --pattern serverless_web --region us-central1" appears twice verbatim), and the Quick Start section re-describes the four pattern stacks already listed in Step 2. Mostly efficient but should be tightened, matching the 3 anchor; not 2 because there is no explanation of things Claude already knows.

3 / 5

Actionability

Every step gives executable, verified commands — the script invocations match the actual argparse flags in the bundled scripts (--input, --resources/--monthly-spend, --app-name/--pattern/--region), plus copy-paste gcloud commands, a full Terraform example, a cloudbuild.yaml, a concrete input JSON format, and worked example outputs. Matches the 5 anchor: fully executable, copy-paste ready, covering common cases.

5 / 5

Workflow Clarity

A clearly sequenced 6-step workflow with an explicit "Validation checkpoint: Confirm the recommended pattern matches the team's operational maturity..." after pattern selection, a full feedback loop in Step 6 ("If deployment fails" → check failure reason via gcloud/logging → fix → redeploy), and a common-failure-causes list for error recovery. Matches the 5 anchor (clear sequence, explicit validation, feedback loops).

5 / 5

Progressive Disclosure

All three referenced files exist and match the advertised contents (architecture_patterns.md, service_selection.md, best_practices.md), referenced one level deep and clearly signaled via "See references/architecture_patterns.md" inline plus a Reference Documentation table. Not 5 because the ~440-line body inlines full templates (the 57-line Terraform block, complete cloudbuild.yaml, and gcloud deployment commands) that overlap content already in the references, and the reference table is buried at the end rather than near the point of use.

4 / 5

Total

17

/

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 description with explicit what/when structure, natural trigger terms covering the main use cases, and a clearly bounded GCP niche. The only weakness is modest coverage of the skill's IaC-generation, CI/CD, and security-review capabilities, which leaves a few natural trigger terms (Terraform, CI/CD) unsurfaced.

DimensionReasoningScore

Specificity

Quotes multiple concrete actions — "Design GCP architectures", "deploy to GKE or Cloud Run", "configure BigQuery pipelines", "optimize GCP costs", "migrate to GCP" — clearly above the 3 anchor (only 1-2 actions). Not 5 because coverage has minor gaps: the skill also generates Terraform IaC, sets up CI/CD, and performs security review, none of which the description hints at.

4 / 5

Completeness

Explicitly answers both questions: what ("Design GCP architectures for startups and enterprises... Covers Cloud Run, GKE, Cloud Functions, Cloud SQL, BigQuery, and cost optimization") and when ("Use when asked to design Google Cloud infrastructure, deploy to GKE or Cloud Run, configure BigQuery pipelines, optimize GCP costs, or migrate to GCP") with concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Strong natural keywords users would say: "GCP" and "Google Cloud" (synonym pair), "GKE", "Cloud Run", "BigQuery", "optimize GCP costs", "migrate to GCP". Not 5 because common phrasings for major capabilities are missing — e.g., "Terraform" or "infrastructure as code", and "CI/CD" / "Cloud Build" — which a user asking for IaC or pipelines would naturally say.

4 / 5

Distinctiveness Conflict Risk

Clear niche (GCP architecture with named Google services) with distinct triggers; a user mentioning GKE, Cloud Run, or BigQuery would not be routed to the AWS or Azure equivalents. Minimal conflict risk, matching the 5 anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alirezarezvani/claude-skills

Path

engineering-team/skills/gcp-cloud-architect/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.