CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aws-cdk-development

AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure programmatically. Covers CDK app structure, construct patterns, stack composition, and deployment workflows.

Quality

84%

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

63%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 well-structured with concrete, executable code and a clearly sequenced, validation-heavy workflow, and it uses its bundle files correctly for progressive disclosure. Its main weakness is redundancy: MCP usage is explained three times and several sections restate the description or generic knowledge Claude already has.

Suggestions

Consolidate the three MCP sections ('Integrated MCP Servers', 'Using MCP Servers Effectively', 'MCP Usage Best Practices') into a single concise section — the current repetition spans roughly 80 lines of duplicated guidance.

Remove the 'When to Use This Skill' section, which restates the frontmatter description, and drop the generic 'Stack Organization' and 'Testing Strategy' bullet lists in favor of a pointer to references/cdk-patterns.md, which already covers these topics.

Add an explicit feedback loop to the validation workflow (e.g., 'If cdk-nag or the build fails, fix the reported rule violations and re-run cdk synth before proceeding') to complete the validate → fix → retry cycle.

DimensionReasoningScore

Conciseness

MCP-server guidance is stated three times ('Integrated MCP Servers', 'Using MCP Servers Effectively' with overlapping example scenarios, and 'MCP Usage Best Practices'), 'When to Use This Skill' restates the frontmatter description almost verbatim, and 'Stack Organization'/'Testing Strategy' offer generic advice Claude already knows ('Unit test individual constructs', 'Use nested stacks for complex applications'). This matches 'Noticeably verbose; several unnecessary explanations or padded sections'; it is not score 1 because the core sections (naming, Lambda constructs, validation layers) are concrete and free of conceptual tutorial padding.

2 / 5

Actionability

Mostly executable guidance: real install/setup commands ('npm install --save-dev cdk-nag', Aspects wiring, NagSuppressions with a documented reason, 'cdk synth', 'npm test', './scripts/validate-stack.sh') and copy-pasteable construct examples for NodejsFunction and PythonFunction. It is not score 5 because the naming examples use '// ...' placeholders and the NodejsFunction example sets a redundant 'handler' prop; not score 3 because nothing is pseudocode — the gaps are minor.

4 / 5

Workflow Clarity

The 8-step Development Workflow sequences Design → Verify → Implement → Validate → Synthesize → Review → Deploy → Verify, and the three-layer validation strategy (IDE feedback, synthesis-time cdk-nag, pre-commit build/tests/script) provides explicit checkpoints before deployment. It is not score 5 because no explicit error-recovery feedback loop is stated (e.g., 'if cdk-nag fails, fix and re-synth') — error handling is only implied via NagSuppressions; not score 3 because the checkpoints are explicit and well-sequenced, not implicit.

4 / 5

Progressive Disclosure

SKILL.md acts as an overview: detailed patterns are deferred to a clearly signaled one-level-deep reference ('File: references/cdk-patterns.md' with a summary of its contents) and the validation script path ('scripts/validate-stack.sh') is named in both the workflow and an 'Additional Resources' section — both files verified to exist, and cdk-patterns.md contains only internal anchor links (no nested references). Core guidance (naming, Lambda construct choice, validation layers) is appropriately kept inline, matching 'Clear overview with well-signaled one-level-deep references; content appropriately split'.

5 / 5

Total

15

/

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: third-person, concrete, and explicit about both capabilities and trigger conditions, with excellent natural keyword coverage including CLI subcommands. The only weakness is the minor trigger overlap introduced by naming CloudFormation alongside CDK-specific terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "building cloud infrastructure with TypeScript/Python", "creating CDK stacks, defining CDK constructs, implementing infrastructure as code", "define AWS infrastructure programmatically" — plus coverage areas (app structure, construct patterns, stack composition, deployment workflows). This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage'; it is not score 4 because no meaningful capability area of the skill's scope is left unmentioned.

5 / 5

Completeness

It explicitly answers both questions: what ('AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python... Covers CDK app structure, construct patterns, stack composition, and deployment workflows') and when ('Use when creating CDK stacks... or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy'). This mirrors the score-5 anchor example almost exactly; score 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Trigger terms include natural synonyms and CLI commands users would actually say: "CDK", "CloudFormation", "IaC", "cdk synth", "cdk deploy", "infrastructure as code", "AWS infrastructure". This matches 'Comprehensive coverage of natural terms including synonyms' — the full phrase 'infrastructure as code' and the cdk CLI subcommands are exactly what a user would type; nothing common is missing.

5 / 5

Distinctiveness Conflict Risk

The niche is clear ('AWS Cloud Development Kit (CDK) expert') with distinct triggers like 'cdk synth', 'cdk deploy', and 'CDK constructs', but listing 'CloudFormation' as a trigger term creates minor overlap risk with a hypothetical raw-CloudFormation/template skill, since a user asking to 'write a CloudFormation template' would trigger this CDK skill. This fits 'Mostly distinct; minor overlap risk with closely related skills' — score 5 would require minimal conflict risk, and the CloudFormation mention is a genuine, if small, overlap.

4 / 5

Total

19

/

20

Passed

Validation

100%

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

Microck/ordinary-claude-skills

Path

skills_all/aws-skills/skills/aws-cdk-development/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.