aws-transform

Performs code upgrades, migrations, and transformations using the AWS Transform (ATX) CLI. Use when upgrading language versions, migrating AWS SDKs, migrating frameworks (Angular, Vue.js, Spring Boot, React), upgrading libraries, optimizing performance, migrating x86 to Graviton, analyzing codebases / generating documentation, or defining custom transformations with natural language. Runs locally on a few repositories or at scale across hundreds via AWS Batch/Fargate.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced skill body with strong validation checkpoints for risky AWS/batch operations. Its weaknesses are token redundancy from repeated guardrails and heavy inline detail that could be externalized into the existing reference files.

Suggestions

Consolidate the repeated consent/wait guidance into a single source (Philosophy OR Critical Rules OR Guardrails) and reference it, rather than restating 'Do NOT proceed until...' and 'Wait for the user' across three sections.

Move the Dockerfile customization procedure (Step 6, ~100 lines) and the full private-repo Secrets Manager credential flows into references/remote-execution.md, leaving the SKILL.md body with the decision logic and a link.

Extract the S3 bucket input handling (zip copy/sync + local extraction) into references/multi-transformation.md or repo-analysis.md so the main workflow stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands and avoids explaining concepts Claude already knows, but it repeats the same consent/wait guardrails across Philosophy, Critical Rules, and Guardrails ('Do NOT proceed until...', 'Wait for the user') and could be tightened; not every token earns its place.	2 / 3
Actionability	Packed with copy-paste-ready bash commands, exact flag formats (e.g. --payload '...' --cli-binary-format raw-in-base64-out), Dockerfile snippets, and verification commands, matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clearly sequenced Prerequisites (0-6) then Workflow Steps 1-8 with explicit validation checkpoints ('Do NOT proceed until aws sts get-caller-identity succeeds', re-run to verify) and feedback loops for destructive/batch operations, so it is not capped at 2.	3 / 3
Progressive Disclosure	Seven real reference files are well-signaled via inline links and a 'When to Use' table (good one-level-deep navigation), but the ~840-line body inlines large blocks that belong in references (Dockerfile customization, full Secrets Manager private-repo flows, S3 input handling), so content that should be separate remains inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 states concrete capabilities and provides an explicit 'Use when' trigger clause covering natural user phrasing. It is distinctive to the ATX tool and unlikely to fire for the wrong skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'upgrading language versions, migrating AWS SDKs, migrating frameworks (Angular, Vue.js, Spring Boot, React), upgrading libraries, optimizing performance, migrating x86 to Graviton, analyzing codebases / generating documentation', matching the anchor for several specific concrete actions.	3 / 3
Completeness	Clearly answers 'what' ('Performs code upgrades, migrations, and transformations using the AWS Transform (ATX) CLI') and 'when' via an explicit 'Use when...' clause enumerating triggers, satisfying the top anchor.	3 / 3
Trigger Term Quality	Natural phrasing a user would actually say is well covered ('upgrading language versions', 'migrating AWS SDKs', 'migrating frameworks', 'upgrading libraries', 'optimizing performance', 'migrating x86 to Graviton', 'analyzing codebases'), with common variations present.	3 / 3
Distinctiveness Conflict Risk	The niche is tightly bound to a named tool (AWS Transform / ATX CLI) with specific triggers (AWS SDKs, Graviton, named frameworks), making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (843 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/migration-and-modernization-skills/aws-transform/SKILL.md
Commit: 222ce56

Reviewed: 3 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.