genkit-infra-expert

Execute use when deploying Genkit applications to production with Terraform. Trigger with phrases like "deploy genkit terraform", "provision genkit infrastructure", "firebase functions terraform", "cloud run deployment", or "genkit production infrastructure". Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is concise and well-structured as an overview, but the core instructions stay abstract without inline executable code or commands, and the deployment workflow lacks explicit validation/feedback checkpoints. Progressive disclosure is partially realized — some referenced paths are broken or a detailed file is unlinked — so it does not reach the top anchors.

Suggestions

Add a minimal inline Terraform snippet or a concrete command (e.g. 'bash ${CLAUDE_SKILL_DIR}/scripts/init-terraform.sh <PROJECT_ID>') to the Instructions so the body is actionable without requiring the reference files.

Insert an explicit validation checkpoint with a feedback loop into the workflow (e.g. 'terraform plan', review errors, re-apply) for the destructive provisioning steps, rather than only the vague final 'Test Genkit flows'.

Fix navigation: link implementation.md from the body (it contains the module structure and advanced patterns) and remove or correct the non-existent '${CLAUDE_SKILL_DIR}/genkit-examples/' reference so all referenced paths resolve to real files.

Dimension	Reasoning	Score
Conciseness	The body is lean — terse Overview, Prerequisites, an 8-item instruction list, and short Output/Error Handling/Examples sections — with no padding or explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	The instruction list ('Configure Terraform Backend: Set up remote state in GCS', 'Provision Compute: Deploy functions or containers') is high-level and abstract with no code or commands in the body itself; concrete, executable guidance lives only in the referenced files, fitting the 'some concrete guidance but incomplete' anchor rather than copy-paste ready.	2 / 3
Workflow Clarity	Eight steps are clearly sequenced, but for a destructive/batch infrastructure-provisioning operation there are no explicit validation checkpoints or fix-and-retry feedback loops; step 8 ('Validate Deployment: Test Genkit flows via HTTP endpoints') is vague with no error-recovery path, capping clarity at 2.	2 / 3
Progressive Disclosure	The body points to real one-level-deep references (errors.md, examples.md) which exist in the bundle, but the referenced 'genkit-examples/' directory does not exist and implementation.md (a real, detailed file) is never linked from the body, so navigation/signaling is inconsistent rather than cleanly one-level and complete.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 specific, trigger-rich, complete, and distinctive, using third person and explicit 'Use when'-style trigger guidance. It fully meets the top anchors on every dimension; only minor cosmetic issues (awkward 'Execute use when' phrasing and trailing whitespace) keep it from being flawless prose.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows', matching the anchor for naming several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (provisioning Firebase Functions, Cloud Run, GKE, monitoring, CI/CD) and 'when' via the explicit 'Trigger with phrases like...' guidance, satisfying the both what-and-when anchor.	3 / 3
Trigger Term Quality	Provides natural trigger phrases users would actually say ('deploy genkit terraform', 'provision genkit infrastructure', 'firebase functions terraform'), giving good coverage of likely phrasings; not just jargon.	3 / 3
Distinctiveness Conflict Risk	The Genkit + Terraform + production infrastructure niche is clearly defined with distinct triggers, making conflict with unrelated skills unlikely; below would require more generic overlap which is absent.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
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/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.