CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

74%

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 ./.gemini/skills/gcp-cloud-architect/SKILL.md

The canonical home for this skill is gcp-cloud-architect in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

56%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-structured with a clear 6-step workflow, an explicit validation checkpoint, deployment-failure feedback loops, and concrete gcloud/Terraform/YAML examples. Its main weakness is that every referenced bundle file is missing, so the workflow's central script commands and 'See references/…' pointers are dead ends, and several sections repeat content already presented earlier.

Suggestions

Ship the referenced bundle files (references/architecture_patterns.md, service_selection.md, best_practices.md and scripts/architecture_designer.py, cost_optimizer.py, deployment_manager.py) — they are referenced throughout but no references/ or scripts/ directory exists, leaving every 'See references/…' callout and script invocation as a dead end.

Either bundle the three Python scripts or replace the workflow's 'python scripts/*.py' commands with the inline gcloud/Terraform steps so that Steps 2–4 are executable exactly as written.

Consolidate the redundant sections: Tools re-lists the scripts already invoked in Steps 2–4, Quick Start repeats the Step 2 patterns, and Input Requirements re-lists the Step 1 bullets as a table plus JSON — keep one canonical presentation of each.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but several sections restate earlier material: Tools re-lists the three scripts already invoked in Steps 2–4, Quick Start repeats the Step 2 patterns, and Input Requirements re-lists the Step 1 bullets as a table plus JSON.

3 / 5

Actionability

Inline gcloud, Terraform HCL, and cloudbuild.yaml examples are concrete and executable, but the workflow's central commands (python scripts/architecture_designer.py, cost_optimizer.py, deployment_manager.py) reference scripts that are not bundled, leaving the headline steps non-executable as written.

3 / 5

Workflow Clarity

A clear 6-step sequence with an explicit Step 2 validation checkpoint, a Step 6 deployment-failure feedback loop (check → review → fix → redeploy), and checklists; the minor gap is the absence of a hard IaC validate/plan gate before apply and the soft, judgment-based nature of the Step 2 checkpoint.

4 / 5

Progressive Disclosure

Sectioning and reference signaling are good (a Reference Documentation table with contents), but all six referenced bundle files — three reference docs and three Python scripts — are absent, so the 'See references/…' callouts are dead ends and large template content is inlined while the promised detail files are missing.

3 / 5

Total

13

/

20

Passed

Description

92%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.

The description is strong: it opens with a concrete capability statement, includes an explicit 'Use when…' trigger clause covering five distinct GCP tasks, names specific services, and uses the Google Cloud/GCP synonym pair. Trigger keyword coverage is very good, though a few natural synonyms (Kubernetes, Google Cloud Platform) are absent.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Design GCP architectures", "deploy to GKE or Cloud Run", "configure BigQuery pipelines", "optimize GCP costs", "migrate to GCP" — plus an enumerated service list, giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Clearly answers both 'what' ("Design GCP architectures for startups and enterprises") and 'when' via an explicit "Use when asked to..." clause with five concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural trigger terms including the Google Cloud/GCP synonym pair plus service names users actually say (GKE, Cloud Run, BigQuery), but a few natural synonyms (Kubernetes, Google Cloud Platform, serverless) are absent, fitting the 'good coverage, a few missing' anchor rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

GCP-specific service names (GKE, Cloud Run, BigQuery, Cloud Functions, Cloud SQL) and the GCP/Google Cloud triggers create a clear niche with minimal overlap risk against sibling AWS/Azure architect skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 11 missing

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
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.