CtrlK
BlogDocsLog inGet started
Tessl Logo

terraform-aws

Comprehensive AWS infrastructure management with Terraform. Covers provider configuration, state management (S3 backend with native locking in Terraform 1.11+), common resource patterns (VPC, IAM, S3, RDS, EKS), module usage, and production best practices. Use when provisioning AWS infrastructure, managing Terraform state, creating VPCs, configuring IAM roles/policies, deploying databases, or troubleshooting Terraform/AWS issues.

64

Quality

80%

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 ./.claude/skills/terraform-aws/SKILL.md

The canonical home for this skill is terraform-aws in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

Highly actionable skill content with excellent copy-paste-ready HCL patterns, real one-level-deep references, and a useful troubleshooting table, but it is noticeably verbose due to multiple duplicated sections and inline CLI material Claude already knows, and its workflows lack explicit validation checkpoints for destructive state operations.

Suggestions

Remove duplicated sections: the S3 backend config (Quick Start vs State Management), the VPC module block (Common Resource Patterns vs Module Usage), default_tags (Quick Start vs Best Practices), environment-conditional RDS logic (RDS pattern vs Best Practices), and the init/plan/apply/workspace commands (Common Workflows vs Quick Reference Commands) each appear twice — keep one canonical location and cross-reference it.

Move the 'Quick Reference Commands' CLI listing and the detailed Module Usage patterns into a reference file (e.g., references/cli-reference.md); Claude already knows core terraform commands, so these inline sections cost context without adding value.

Add explicit validation checkpoints to risky workflows: after 'terraform import', verify with 'terraform plan' (expect no changes); before 'terraform apply tfplan', confirm the plan was reviewed; and warn that 'terraform state rm/mv' should be followed by a plan check — this would lift workflow clarity past the destructive-operation cap.

DimensionReasoningScore

Conciseness

The ~630-line body contains several padded/duplicated sections: the S3 backend block appears in both Quick Start and State Management, the VPC module block appears in both Common Resource Patterns and Module Usage, default_tags appears twice, environment-conditional RDS logic is repeated in Best Practices, and init/plan/apply/workspace commands are listed in both Common Workflows and Quick Reference Commands. Additionally, the Quick Reference Commands section documents terraform CLI basics (fmt, validate, plan, output) that Claude already knows, matching anchor 2 ('noticeably verbose; several unnecessary explanations or padded sections') rather than anchor 3, where redundancy would be isolated.

2 / 5

Actionability

Guidance is fully executable: complete copy-paste-ready HCL for provider/backend config, VPC module, S3 encryption/versioning/public-access-block, IAM role with inline jsonencode policies, and RDS with environment conditionals; plus concrete commands for init/plan/apply, import with example resource IDs, and a specific troubleshooting table ('terraform force-unlock <lock-id>'). The few undefined variables (db_name, db_username, cost_center) follow standard Terraform convention and the skill demonstrates variable declaration patterns itself, so this matches anchor 5 rather than anchor 4.

5 / 5

Workflow Clarity

Common Workflows provides a rough init → plan -out → apply tfplan sequence and workspace/import commands, but validation checkpoints are missing or only implicit for destructive and state-manipulating operations: no 'terraform plan to verify' step after import, no verification after 'terraform state rm/mv', and 'terraform apply -auto-approve' / 'terraform destroy' carry only a caution comment. Per the rubric cap for destructive/batch workflows lacking validation, this is capped at anchor 3 ('sequence present but checkpoints missing or implicit') rather than 4.

3 / 5

Progressive Disclosure

Structure is good: all three referenced files (references/vpc-networking.md, references/iam-security.md, references/state-management.md) exist, are one level deep, and the 'Detailed Documentation' section signals each with a bullet list of its contents. Not a 5 because significant detail that belongs in the reference files is inlined in SKILL.md (full module usage patterns, the entire CLI quick-reference, complete RDS configuration), leaving the main file heavier than an overview should be — matching anchor 4 ('most content is appropriately placed; minor organization gaps') over anchor 5 ('content appropriately split').

4 / 5

Total

14

/

20

Passed

Description

92%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 clearly and explicitly states both what the skill covers and when to use it, with concrete AWS/Terraform-specific trigger phrases. Only weakness is slightly incomplete synonym coverage in trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete coverage areas: 'provider configuration, state management (S3 backend with native locking in Terraform 1.11+), common resource patterns (VPC, IAM, S3, RDS, EKS), module usage, and production best practices' — comprehensive and specific, matching the anchor-5 example structure. It is not the level below (4) because coverage spans all major AWS/Terraform domains with only 'production best practices' being marginally generic.

5 / 5

Completeness

It explicitly answers both 'what' ('Covers provider configuration, state management..., common resource patterns..., module usage, and production best practices') and 'when' ('Use when provisioning... or troubleshooting Terraform/AWS issues') with concrete trigger phrases, matching the anchor-5 exemplar. Neither component is missing or weak.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ('Use when provisioning AWS infrastructure, managing Terraform state, creating VPCs, configuring IAM roles/policies, deploying databases, or troubleshooting Terraform/AWS issues'), giving good keyword coverage. Not a 5 because some natural variations users would say are missing (e.g., 'infrastructure as code', 'IaC', 'setting up EC2', 'EKS cluster', 'spinning up instances').

4 / 5

Distinctiveness Conflict Risk

The Terraform-on-AWS pairing with named resources (VPC, IAM, S3, RDS, EKS, S3 backend) carves a clear niche with distinct triggers and minimal overlap risk with unrelated skills. It sits above level 4 because the trigger terms (Terraform state, IAM roles/policies, VPC provisioning) are specific to this exact skill rather than a broad document/file domain.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (634 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.