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.
67
61%
Does it follow best practices?
Impact
Pending
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 capabilities, explicit trigger phrases, and clear 'when to use' guidance. The only minor issue is the slightly awkward opening 'Execute use when' phrasing, but the content is comprehensive and well-structured.
| 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'. Good coverage of natural variations combining the key technologies. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche combining Genkit + Terraform + specific cloud infrastructure targets. Unlikely to conflict with generic deployment or generic Terraform skills due to the Genkit-specific focus and enumerated services. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
22%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 actionable content in the main file. It provides no Terraform code, no concrete commands, and no specific configuration examples — everything meaningful is deferred to reference files. The workflow steps are abstract descriptions rather than executable instructions, which is particularly problematic for infrastructure deployment where validation and error recovery are critical.
Suggestions
Add at least one complete, executable Terraform example (e.g., a minimal Cloud Run deployment for a Genkit app) directly in the SKILL.md so Claude has immediate actionable guidance.
Include specific CLI commands for each workflow step (e.g., 'terraform init -backend-config=...', 'gcloud secrets versions add ...') instead of abstract descriptions.
Add explicit validation checkpoints with concrete commands between deployment steps, such as 'terraform plan -out=tfplan' before apply, and 'curl https://<endpoint>/health' after deployment.
Remove the prerequisites list items that Claude already knows (like 'Understanding of Genkit flows') and replace with specific version constraints or configuration values that are genuinely needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The prerequisites section includes items Claude would already know or could infer (e.g., 'Understanding of Genkit flows and deployment options'). The Output section is generic boilerplate. However, it's not excessively verbose overall. | 2 / 3 |
Actionability | The instructions are entirely abstract and vague — 'Choose Deployment Target', 'Configure Terraform Backend', 'Provision Compute' — with zero concrete code, commands, or Terraform snippets. There is nothing executable or copy-paste ready; all actual content is deferred to reference files. | 1 / 3 |
Workflow Clarity | While steps are numbered, they lack any specificity, validation checkpoints, or feedback loops. For infrastructure deployment (a destructive/risky operation), there are no explicit validation steps between provisioning stages, no error recovery guidance, and the 'Validate Deployment' step is vague. | 1 / 3 |
Progressive Disclosure | References to external files (implementation.md, errors.md, examples.md) are present and one-level deep, which is good. However, the main SKILL.md contains almost no substantive content — it's essentially an empty shell pointing elsewhere, making the overview itself unhelpful as a quick-start guide. | 2 / 3 |
Total | 6 / 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
70e9fa4
- 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.