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.
48
53%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/devops/jeremy-genkit-terraform/skills/genkit-infra-expert/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly defines its niche at the intersection of Genkit and Terraform deployment. It provides specific concrete actions, explicit trigger phrases, and clear when/what guidance. The only minor issue is the slightly awkward opening 'Execute use when' which could be smoother, but it doesn't materially impact functionality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows.' These are concrete, specific infrastructure components. | 3 / 3 |
Completeness | Clearly answers both what ('Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows') and when ('use when deploying Genkit applications to production with Terraform') with explicit trigger phrases listed. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'deploy genkit terraform', 'provision genkit infrastructure', 'firebase functions terraform', 'cloud run deployment', 'genkit production infrastructure'. These cover multiple natural variations combining the key technologies. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Genkit + Terraform + specific infrastructure targets (Firebase Functions, Cloud Run, GKE). Unlikely to conflict with generic Terraform or generic deployment skills due to the specific Genkit + AI workflow focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a table of contents with no substantive content. It lacks any executable code, concrete Terraform configurations, or specific commands—everything is described at a high level that provides no actionable guidance beyond what Claude already knows. The referenced bundle files (implementation.md, errors.md, examples.md) do not exist, making the progressive disclosure structure hollow.
Suggestions
Add concrete, executable Terraform HCL snippets for at least one deployment target (e.g., Cloud Run) including provider configuration, resource definitions, and Secret Manager integration.
Replace the abstract 8-step workflow with specific commands and validation checkpoints, e.g., 'terraform plan' output review before 'terraform apply', and 'gcloud run services describe' to verify deployment.
Remove the prerequisites section or reduce it to a single line—Claude doesn't need to be told what Terraform is or that CLIs need authentication.
Either provide the referenced bundle files (implementation.md, errors.md, examples.md) with real content, or inline the essential guidance directly in SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The prerequisites section explains things Claude already knows (what Terraform is, that CLIs need authentication). The instructions are high-level descriptions that add no value beyond what Claude could infer. The 'Output' section describes generic deliverables rather than concrete specifications. | 1 / 3 |
Actionability | No executable code, no Terraform snippets, no concrete commands, no specific configurations. Every instruction is vague and abstract (e.g., 'Configure Terraform Backend: Set up remote state in GCS' without any HCL code or gcloud commands). This describes rather than instructs. | 1 / 3 |
Workflow Clarity | The 8 steps are a high-level outline with no validation checkpoints, no feedback loops, and no error recovery guidance. For infrastructure deployment—a destructive/risky operation—there are no explicit validation steps between provisioning stages, and 'Validate Deployment' is just a vague final step. | 1 / 3 |
Progressive Disclosure | References to implementation.md, errors.md, and examples.md are clearly signaled and one level deep, which is good structure. However, no bundle files exist to back these references, and the main SKILL.md itself contains almost no substantive content—it's an empty shell pointing to files that don't exist. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
69c73e9
- 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.