CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gcp-pipeline-resource-provisioning

Automates declarative resource creation and provisioning for data pipelines, supporting BigQuery, Dataform, Dataproc, BigQuery Data Transfer Service (DTS), and other resources. It manages environment-specific configurations (dev, staging, prod) through a deployment.yaml file. Use when: - Modifying or creating deployment.yaml for deployment settings. - Resolving environment-specific variables (e.g., Project IDs, Regions) for deployment. - Provisioning supported infrastructure like BigQuery datasets/tables, Dataform resources, or DTS resources via deployment.yaml. Do not use when: - Resources already exist. - Managing resources not supported by `gcloud beta orchestration-pipelines resource-types list`. - Managing general cloud infrastructure (VMs, networks, Kubernetes, IAM policies), which are better suited for Terraform. - Infrastructure spans multiple cloud providers (AWS, Azure, etc.). - Already uses Terraform for the target resources.

Quality

89%

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

82%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 content is a well-sequenced, highly actionable workflow: concrete gcloud discovery/validate/deploy commands, a mandatory-labels rule with exact values, strict secret-handling policy, and a verifiable Definition of Done, with the deployment.yaml template properly split into a single reference file. Its weaknesses are modest — a redundant secrets section, no explicit fix-and-revalidate loop after the validation step, and an inconsistent reference path between Steps 1 and 3.

Suggestions

Consolidate the overlapping secrets bullets (No Creation, Reference Only Policy, Safe Deployment, Manual Secret Management) into 2-3 directives stating the rule once: never create/read secrets, only reference them via {{ SECRET_NAME }} and ask the user to create missing ones.

Add an explicit feedback loop after Step 4: 'If validation fails, read the error output, fix deployment.yaml, and re-run gcloud beta orchestration-pipelines validate before deploying.'

Fix the reference path in Step 1 to match the actual bundle filename (references/gcp_pipeline_resource_provisioning_spec.md with underscores) and cite the file once instead of twice (Steps 1 and 3).

DimensionReasoningScore

Conciseness

The body is command-heavy and directive ("gcloud config get project", "You MUST ask the user for the environment name", exit-code-0 Definition of Done) with little explanation of concepts Claude already knows, fitting 'efficient; minor instances that could be trimmed'. It is not score 5 because the secrets block restates one rule several times across overlapping bullets ("No Creation", "Reference Only Policy", "Safe Deployment", "Manual Secret Management") and Steps 1 and 3 both point to the same reference spec, which could be consolidated.

4 / 5

Actionability

Quotes: copy-paste-ready commands ("gcloud projects describe $(gcloud config get project) --format=\"value(projectNumber)\"", "gcloud beta orchestration-pipelines validate --environment=<ENV_NAME>", "gcloud beta orchestration-pipelines deploy --environment=<ENV_NAME> --local"), exact label values ("datacloud: \"antigravity\""), substitution syntax ("{{ VARIABLE_NAME }}"), and a concrete "Definition of Done". Guidance is fully executable with specifics covering the common cases, matching the top anchor; resource-definition templates are appropriately delegated to the bundled spec file.

5 / 5

Workflow Clarity

Quotes: a clear five-step sequence ("Step 1: Supported Resource Types" through "Step 5: Deployment"), an explicit validation gate ("The agent MUST validate the deployment.yaml before generating the deployment script"), and a Definition of Done checklist ("executes successfully (exit code 0)"). This fits 'clear sequence with most checkpoints present; minor validation gaps' — it is above score 3 because validation is explicit, but below score 5 because the error-recovery feedback loop (what to do when validation fails: fix and re-validate) is never spelled out.

4 / 5

Progressive Disclosure

The bundle contains one reference file (references/gcp_pipeline_resource_provisioning_spec.md, 108 lines of deployment.yaml templates) that is one level deep and clearly signaled from the body ("Refer to: references/gcp-pipeline-resource-provisioning_spec.md"). Structure is good with the bulk template content correctly split out, but Step 1 cites the file with hyphens ('gcp-pipeline-resource-provisioning_spec.md') while the actual filename and the Step 3 citation use underscores, a navigation inconsistency that keeps it below the 'easy navigation' top anchor.

4 / 5

Total

17

/

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 states concrete capabilities across named GCP services, uses third person, and provides an explicit 'Use when' trigger list plus a 'Do not use when' boundary list that sharply reduces conflict risk with Terraform and general cloud-infrastructure skills. The only weakness is keyword coverage that misses a few natural synonyms a user might say.

DimensionReasoningScore

Specificity

Quotes: "Automates declarative resource creation and provisioning", "manages environment-specific configurations (dev, staging, prod) through a deployment.yaml file", "Provisioning supported infrastructure like BigQuery datasets/tables, Dataform resources, or DTS resources via deployment.yaml". Multiple concrete actions are named across specific GCP services and a concrete artifact (deployment.yaml), matching the 'comprehensive coverage' anchor; it is clearly above score 4 ('several specific actions, minor gaps') since actions, services, and resource types are all enumerated.

5 / 5

Completeness

Quotes: what — "Automates declarative resource creation and provisioning for data pipelines, supporting BigQuery, Dataform, Dataproc, BigQuery Data Transfer Service (DTS)"; when — an explicit "Use when:" list with concrete triggers ("Modifying or creating deployment.yaml", "Resolving environment-specific variables") plus a "Do not use when" boundary list. Both what and when are answered explicitly with concrete trigger phrases, exactly matching the top anchor; not score 4 because the 'when' is already fully explicit, not merely present.

5 / 5

Trigger Term Quality

Quotes: "deployment.yaml", "BigQuery datasets/tables", "Dataform", "DTS", "dev, staging, prod", "Project IDs, Regions". Keyword coverage is good and includes the natural file trigger 'deployment.yaml' and service names users would say, but a few natural variations are missing (e.g., 'GCP', 'data pipeline deployment', 'staging vs stage'), so it fits 'good coverage; a few natural terms missing' rather than the fully comprehensive anchor with synonyms/extensions.

4 / 5

Distinctiveness Conflict Risk

Quotes: "Managing general cloud infrastructure (VMs, networks, Kubernetes, IAM policies), which are better suited for Terraform", "Infrastructure spans multiple cloud providers", "Resources already exist". The niche (deployment.yaml-based provisioning for GCP orchestration pipelines) is distinct and the explicit exclusion list actively prevents conflicts with adjacent tools like Terraform, matching 'clear niche with distinct triggers; minimal conflict risk'.

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

saski/arnesto

Path

.agents/skills/gcp-pipeline-resource-provisioning/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.