oma-tf-infra

Infrastructure-as-code specialist for multi-cloud provisioning using Terraform across any provider (AWS, GCP, Azure, Oracle Cloud). Use for terraform plan/apply, state management, compute, databases, storage, networking, IAM, OIDC, cost optimization, policy-as-code, ISO/IEC 42001 AI controls, ISO 22301 continuity, and ISO/IEC/IEEE 42010 architecture documentation.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%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.

A well-structured, action-oriented skill body with strong workflow sequencing and validation gates for destructive Terraform operations. It would tighten by dropping the abstract scene/SSL-primitive scaffolding and ensuring the referenced resources/ and ../_shared/ bundles actually ship alongside it.

Suggestions

Trim the abstract scaffolding — the PREPARE/ACQUIRE/REASON/ACT/VERIFY/FINALIZE scene labels and the Actions × SSL-primitive table restate the workflow in a meta-model Claude doesn't need; keep the concrete Entry/VERIFY/Transitions flow and drop the rest.

Ship the referenced bundle files (resources/multi-cloud-examples.md, cost-optimization.md, policy-testing-examples.md, iso-42001-infra.md, checklist.md, execution-protocol.md, examples.md) and ../_shared/core/*.md so the one-level-deep references actually resolve.

Consolidate the References section — it currently lists the same resources both as prose ('Follow resources/execution-protocol.md ...') and as a bullet list; keep a single clearly-signaled reference block to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but carries abstraction padding Claude doesn't need — the scene framework (PREPARE/ACQUIRE/REASON/ACT/VERIFY/FINALIZE) and the 'Logical Operations' table mapping actions to SSL primitives (READ/SELECT/COMPARE/INFER) describe an internal model rather than instruct Terraform work.	3 / 5
Actionability	Provides concrete executable commands ('terraform fmt -recursive', 'terraform validate', 'terraform plan -out=tfplan', 'checkov -d .', 'tfsec .'), a real multi-cloud resource-mapping table, and specific guardrails ('use for_each over count', 'version pin all providers'), with minor gaps since the bulk of HCL patterns are deferred to external resource files.	4 / 5
Workflow Clarity	Clear sequenced workflow (Entry → PREPARE/ACQUIRE/REASON/ACT/VERIFY/FINALIZE → Transitions → Failure and recovery → Exit) with explicit validation in VERIFY, destructive-change stop points, confirmation gates for production apply/destroy, and error-recovery feedback loops.	5 / 5
Progressive Disclosure	Good overview structure with well-signaled, one-level-deep references (resources/execution-protocol.md, examples.md, multi-cloud-examples.md, etc.), but the references are listed twice (narrative and bullet) and the referenced bundle files do not exist on disk, leaving minor organization and packaging gaps.	4 / 5
	Total	16 / 20 Passed

Description

96%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, third-person description that explicitly pairs a clear 'what' with a concrete 'Use for ...' trigger clause and comprehensive domain keywords. Its only weakness is breadth — multi-cloud plus ISO governance framing slightly raises overlap risk with adjacent cloud and compliance skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities across domains — 'terraform plan/apply, state management, compute, databases, storage, networking, IAM, OIDC, cost optimization, policy-as-code, ISO/IEC 42001 AI controls, ISO 22301 continuity, and ISO/IEC/IEEE 42010 architecture documentation' — giving comprehensive coverage rather than only minor gaps.	5 / 5
Completeness	Explicitly answers both what ('Infrastructure-as-code specialist for multi-cloud provisioning using Terraform across any provider') and when ('Use for terraform plan/apply, state management, ...') with concrete trigger phrases in third person.	5 / 5
Trigger Term Quality	Includes natural terms users say ('terraform plan/apply', 'state management', 'IAM', 'OIDC', 'cost optimization') plus provider acronyms (AWS, GCP, Azure, Oracle Cloud) and synonyms (multi-cloud, Infrastructure-as-code, Terraform), matching comprehensive anchor-5 coverage.	5 / 5
Distinctiveness Conflict Risk	Clear Terraform-IaC niche with distinct triggers, but the 'across any provider' breadth and ISO governance scope create minor overlap risk with general cloud/DevOps and compliance skills, so it sits below the minimal-conflict anchor 5.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: benchmarks/runs/oma/.agents/skills/oma-tf-infra/SKILL.md
Commit: 032c988

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.