CtrlK
BlogDocsLog inGet started
Tessl Logo

terragrunt-generator

Comprehensive toolkit for generating best-practice Terragrunt configurations (HCL files) following current standards and conventions. Generates terragrunt.hcl files, root configurations, child modules, stacks, and environment setups; configures remote state backends, dependency blocks, include blocks, feature flags, exclude blocks, and errors blocks; supports DRY Terraform patterns, multi-environment layouts (dev/staging/prod), and OpenTofu engine integration. Use when creating new Terragrunt projects or resources, scaffolding multi-environment infrastructure, implementing DRY Terraform wrapper configurations, setting up terragrunt.hcl files with remote state or provider config, managing module dependencies, or building infrastructure modules with Terragrunt stacks.

71

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable, well-validated workflow for generating Terragrunt configurations, with executable commands, checklists, and real feedback loops, supported by a genuine one-level-deep bundle. Its main weakness is redundancy — repeated tables and inlined presentation boilerplate — that inflates token cost without adding guidance.

Suggestions

Remove the duplicated template table (Step 3 vs. References) and the duplicated pattern-selection table (Architecture Patterns vs. Step 2), keeping a single canonical copy each.

Move the verbose Presentation Requirements example output (environment variable tables, usage-instruction boilerplate) into a reference file and keep only the required section list in SKILL.md.

Trim the Common Issues bullet list, which restates the troubleshooting.md table of contents that is already linked one line above.

DimensionReasoningScore

Conciseness

The body is mostly dense tables and terse bullets with little explanation of concepts Claude already knows, but it could be tightened: the template-read table appears twice (Step 3 and the References section), the pattern-selection table is duplicated (Architecture Patterns and Step 2), and the Presentation Requirements section inlines verbose boilerplate example output. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the padded anchor 2 or the minor-trim anchor 4.

3 / 5

Actionability

Guidance is fully executable: concrete commands ('terragrunt hcl fmt --check', 'terragrunt stack run apply'), copy-paste-ready HCL snippets (feature flag correct/incorrect pair, exclude block, env.hcl locals), explicit template paths per configuration type, and enumerated placeholders to replace. It matches the top anchor covering the common cases, above the 'concrete code with minor gaps' anchor.

5 / 5

Workflow Clarity

The six-step Generation Workflow is clearly sequenced with a mandatory pre-generation checklist, explicit validation commands after each stage ('terragrunt hcl fmt --check', 'terragrunt dag graph'), and a fix-and-re-validate feedback loop in Step 5. This matches the anchor with explicit validation steps, feedback loops, and checklists for a batch-generation process.

5 / 5

Progressive Disclosure

The bundle is well structured: patterns and troubleshooting live in one-level-deep reference files, templates in assets, each signaled by 'Read before generating' tables with when-to-read columns, and all referenced paths exist. It falls short of the top anchor because the reference/template tables are duplicated within the body and the verbose Presentation Requirements boilerplate is inlined rather than split out — minor organization gaps matching the 'good structure' anchor.

4 / 5

Total

17

/

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 description: it enumerates concrete capabilities in third person, names specific HCL constructs and file types, and closes with an explicit multi-clause 'Use when...' trigger list. The only weakness is slight overlap risk with generic Terraform/OpenTofu requests via phrases like 'DRY Terraform patterns'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Generates terragrunt.hcl files, root configurations, child modules, stacks, and environment setups; configures remote state backends, dependency blocks, include blocks, feature flags, exclude blocks, and errors blocks' — giving comprehensive, not just several, capabilities. It fits the anchor for comprehensive coverage with no meaningful gaps, so it sits above the 'several specific actions; minor gaps' anchor.

5 / 5

Completeness

Both what and when are explicit: the what enumerates generation and configuration capabilities, and the when gives concrete triggers ('Use when creating new Terragrunt projects or resources, scaffolding multi-environment infrastructure, ... setting up terragrunt.hcl files with remote state or provider config'). This clearly matches the top anchor with concrete trigger phrases, not the weaker 'when could be more specific' anchor.

5 / 5

Trigger Term Quality

Natural user phrasing is well covered: 'terragrunt.hcl files', 'multi-environment layouts (dev/staging/prod)', 'DRY Terraform wrapper configurations', 'remote state', 'module dependencies', and 'Terragrunt stacks', including the concrete file name users would mention. This matches the comprehensive-coverage anchor with synonyms and file names rather than the 'a few natural terms missing' anchor.

5 / 5

Distinctiveness Conflict Risk

Terragrunt is named throughout and triggers are Terragrunt-specific, but phrases like 'DRY Terraform patterns' and 'OpenTofu engine integration' create minor overlap risk with plain Terraform or OpenTofu skills. It fits 'mostly distinct; minor overlap risk with closely related skills' better than the clear-niche anchor.

4 / 5

Total

19

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (508 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 15 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
pantheon-org/tekhne
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.