CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/devops/jeremy-genkit-terraform/skills/genkit-infra-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 body is a lean, well-sequenced overview with genuine reference files behind its links, but it reads as a skeleton: no executable commands or code, no intermediate validation checkpoints for a batch infrastructure workflow, and inconsistent reference hygiene (an unlinked pointer to implementation.md, an unmentioned script, and a dead genkit-examples/ path). It is serviceable as a directory but weak as standalone guidance.

Suggestions

Add executable guidance to the Instructions steps: at minimum the terraform init/plan/apply commands and how to run scripts/init-terraform.sh, or link references/implementation.md directly where the HCL lives.

Insert validation checkpoints between steps (e.g., review terraform plan before apply, verify secret access after provisioning) rather than relying solely on the final validation step and the errors.md reference.

Fix reference hygiene: replace "See Terraform implementation details for output format specifications" with a markdown link to references/implementation.md, complete or remove the empty "Genkit Deployment:" resource bullet, and remove or create the nonexistent ${CLAUDE_SKILL_DIR}/genkit-examples/ path.

DimensionReasoningScore

Conciseness

The ~50-line body is efficient and assumes Claude's competence — no explanation of what Terraform or Genkit is — with only minor trimmable fluff ("Understanding of Genkit flows and deployment options", a dangling "Genkit Deployment:" bullet with no URL). Not 5 because those small wasted tokens exist; not 3 because padding is minimal.

4 / 5

Actionability

The 8 steps name concrete technologies ("Set up remote state in GCS", "Store API keys in Secret Manager", "Test Genkit flows via HTTP endpoints") but the body contains no executable code or commands — every step is a one-line directive. Anchor 3 (some concrete guidance, incomplete) fits: more than high-level hints (2), but nothing copy-paste executable (4).

3 / 5

Workflow Clarity

A clear 8-step sequence ends with an explicit validation step ("Validate Deployment: Test Genkit flows via HTTP endpoints"), but for a batch infrastructure operation there are no intermediate checkpoints (e.g., terraform plan review, per-step verification) and no feedback loop in the body — recovery is only outsourced to a reference file. Steps are listed with implicit checkpoints — anchor 3, not 4.

3 / 5

Progressive Disclosure

The body has real, well-linked references ([references/errors.md], [references/examples.md]) but the signal for the main implementation detail is a vague unlinked "See Terraform implementation details" line, scripts/init-terraform.sh is never mentioned, and the body points to ${CLAUDE_SKILL_DIR}/genkit-examples/ which does not exist in the bundle. Some structure with unclear signaling — anchor 3, not 4.

3 / 5

Total

13

/

20

Passed

Description

83%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.

A strong description that explicitly covers both what the skill does and when to use it, with multiple concrete natural-language trigger phrases and a clearly defined Genkit/Terraform niche. Weaknesses are limited: slightly incomplete capability coverage and one generic trigger ("cloud run deployment") that risks overlap with non-Genkit deployment requests.

DimensionReasoningScore

Specificity

"Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows" lists several specific concrete actions, but coverage has gaps — secrets handling, state management, and validation (which the skill itself performs) are unmentioned. This matches anchor 4 (minor gaps) rather than 5 (comprehensive).

4 / 5

Completeness

Both what ("Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD") and when ("Execute use when deploying Genkit applications to production with Terraform. Trigger with phrases like...") are explicitly stated with concrete trigger phrases. This matches anchor 5; the awkward "Execute use when" wording is grammatical noise but the trigger guidance is fully explicit, so 4 would undervalue it.

5 / 5

Trigger Term Quality

Explicit natural phrases like "deploy genkit terraform", "firebase functions terraform", and "cloud run deployment" give good keyword coverage, but common variations (e.g., "gke", "infrastructure as code", "gcloud deploy") are missing. Not 5 because coverage is not comprehensive; not 3 because several natural phrasings users would say are present.

4 / 5

Distinctiveness Conflict Risk

The Genkit + Terraform niche is distinct and most triggers are Genkit-specific, but "cloud run deployment" is a generic phrase that could overlap with a generic Cloud Run deployment skill. Mostly distinct with minor overlap risk — anchor 4, not 5.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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/tons-of-skills-marketplace

Path

plugins/devops/jeremy-genkit-terraform/skills/genkit-infra-expert/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.