CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Low

Low-risk findings worth noting

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.

A highly actionable, well-sequenced operational guide with strong validation checkpoints and a sound reference bundle. Its weaknesses are moderate verbosity (duplicated passages, inline changelog TD list) and a large Dockerfile-customization block that belongs in the remote-execution reference rather than the main file.

Suggestions

Move the Dockerfile customization section (~100 lines, Step 6 remote mode) into references/remote-execution.md next to the deployment instructions it supports, leaving only the decision logic (pre-built vs. custom image) inline.

De-duplicate repeated guidance — e.g., 'If the user declines, suggest local mode as an alternative' appears in both the remote and local halves of Step 6 — and consolidate the recurring 'Do NOT' restatements (Philosophy, Prerequisites, Workflow, Critical Rules) into the single Critical Rules section.

Trim the Changelog's 13-entry TD name list (or move it to a reference file), since supported TDs are discovered dynamically via 'atx custom def list --json' and the static list will go stale.

DimensionReasoningScore

Conciseness

The body is mostly necessary operational detail with no generic-concept padding, but it could be tightened: the sentence 'If the user declines, suggest local mode as an alternative' appears twice (Step 6 remote and local sections), ~100 lines of Dockerfile customization are inlined, and the changelog lists 13 TD names that are reference material.

3 / 5

Actionability

Guidance is fully executable throughout — copy-paste-ready commands for platform detection ('uname -s'), credential verification ('aws sts get-caller-identity'), TD discovery ('atx custom def list --json'), IAM policy attachment, S3 zip sync, and concrete Dockerfile blocks — covering the common cases for both execution modes.

5 / 5

Workflow Clarity

Steps 1–8 are clearly sequenced with explicit validation checkpoints and feedback loops: re-run credential checks after setup, block until 'atx custom def list --json' succeeds, confirm match report and plan with the user, verify target runtimes before executing, and check deployment via CloudFormation. Batch and destructive operations all carry verification, and error-recovery paths (IAM attach failure, SSO roles, merge conflicts) are specified.

5 / 5

Progressive Disclosure

Good structure with seven real, verified reference files, all clearly signaled inline and indexed in a 'When to Use' References table, one level deep. One notable gap: the ~100-line Dockerfile customization section belongs in remote-execution.md alongside the deployment instructions it accompanies, which keeps this below the fully-appropriately-split anchor of 5.

4 / 5

Total

17

/

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: concrete, comprehensive, third-person, with an explicit 'Use when' clause enumerating specific trigger scenarios. Its only weakness is missing common synonyms (modernize, refactor) and concrete language names that users would naturally say.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — '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' — with comprehensive coverage of the tool's capability surface, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

It explicitly answers both 'what' ('Performs code upgrades, migrations, and transformations using the AWS Transform (ATX) CLI') and 'when' via an explicit 'Use when upgrading language versions, migrating AWS SDKs, ...' clause with concrete trigger phrases, in third-person voice — a clear anchor-5 match.

5 / 5

Trigger Term Quality

Natural trigger terms are well covered ('upgrade', 'migrate', framework names, 'Graviton', 'library upgrades'), but common synonyms like 'modernize' or 'refactor' and concrete language names users would say (Java, Python, Node.js) are missing, placing it just below the comprehensive-synonyms anchor of 5.

4 / 5

Distinctiveness Conflict Risk

The AWS Transform (ATX) branding plus specific triggers (AWS SDK migrations, Graviton, ATX CLI) carve out a clear niche with minimal overlap risk against generic migration or code-refactoring skills.

5 / 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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (850 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

mreferre/aws-agent-toolkit-skills

Path

.kiro/skills/aws-transform/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.