CtrlK
BlogDocsLog inGet started
Tessl Logo

gcp

Google Cloud Platform expert for gcloud CLI, GKE, Cloud Run, and managed services

55

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./crates/openfang-skills/bundled/gcp/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The content is concise and well-structured for a single-purpose cloud guidance skill, earning full marks for token efficiency and progressive disclosure. Actionability and workflow clarity sit at 2 because commands are partial placeholders and there are no explicit validation checkpoints.

Suggestions

Complete at least one end-to-end example with real values, e.g. a full 'gcloud run deploy' or GKE cluster create command a user could adapt directly.

Add a sequenced workflow with validation for a risky operation (e.g. IAM least-privilege setup: create SA -> bind roles -> verify with 'gcloud iam roles describe' -> deploy).

Where commands use placeholders, mark them explicitly (e.g. 'replace PROJECT_ID') so Claude knows what to substitute.

DimensionReasoningScore

Conciseness

The body is lean, well-organized into Principles/Techniques/Patterns/Pitfalls, and assumes Claude's competence without explaining what GCP or managed services are; every line carries actionable signal.

3 / 3

Actionability

Provides real gcloud command fragments (e.g. 'gcloud run deploy --image ...', 'gcloud billing budgets create'), but most are partial with placeholders like PROJECT/IMAGE and the patterns describe architecture rather than giving copy-paste-ready complete commands.

2 / 3

Workflow Clarity

Content is organized into clear categories but there is no sequenced multi-step workflow with validation checkpoints for operations (e.g. IAM provisioning, cluster creation) that would benefit from verify-then-proceed loops.

2 / 3

Progressive Disclosure

This is a short, self-contained skill with no bundle files in references/scripts/assets; the sectioned overview is appropriately self-contained and one level deep, satisfying the simple-skill carve-out.

3 / 3

Total

10

/

12

Passed

Description

52%

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 identifies a coherent GCP niche with named tools, but it reads as a persona label rather than trigger guidance. It lacks a 'Use when...' clause and concrete action verbs, capping completeness and specificity at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with Google Cloud Platform, gcloud CLI, GKE, Cloud Run, or GCP managed services like Cloud SQL and Pub/Sub.'

Replace the persona phrasing 'expert for' with concrete third-person actions such as 'Deploys, configures, and troubleshoots GCP infrastructure'.

Expand trigger terms to include natural phrasings users say: 'GCP', 'Google Cloud', 'Terraform for GCP', 'IAM', 'BigQuery', 'Cloud SQL'.

DimensionReasoningScore

Specificity

Names the domain ('gcloud CLI, GKE, Cloud Run, and managed services') and some concrete tools, but uses a single generic verb ('expert for') rather than listing multiple specific actions like deploying, configuring, or diagnosing.

2 / 3

Completeness

Answers 'what' (GCP managed services and tooling) but has no 'Use when...' clause or equivalent trigger guidance; the judging guidelines cap completeness at 2 when explicit trigger guidance is missing.

2 / 3

Trigger Term Quality

Includes relevant product names (gcloud, GKE, Cloud Run) a user might mention, but omits common variations users actually say ('GCP', 'Google Cloud', 'IAM', 'Terraform for GCP', 'BigQuery') that appear in the body.

2 / 3

Distinctiveness Conflict Risk

The GCP focus is a clear niche, but the bare 'managed services' wording and lack of explicit triggers mean it could still overlap with a generic cloud or Terraform skill.

2 / 3

Total

8

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
RightNow-AI/openfang
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.