aws-amplify

Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync/DynamoDB), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock). Supports React, Next.js, Vue, Angular, React Native, Flutter, Swift, and Android. Always use this skill for Amplify Gen2 topics — even for questions you think you know — it contains validated, version-specific patterns that prevent common mistakes. TRIGGER when: user mentions Amplify Gen2; project has amplify/ directory or amplify_outputs; code imports @aws-amplify packages; user asks about defineBackend, defineAuth, defineData, defineStorage, defineFunction, or npx ampx. SKIP: Amplify Gen1 (amplify CLI v6), standalone SAM/CDK without Amplify (use aws-serverless), direct Bedrock without Amplify AI Kit (use bedrock).

1.50x

Quality

93%

Does it follow best practices?

Impact

83%

1.50x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 highly actionable and well-structured, with executable per-framework code and an excellent one-level-deep reference split. The only weakness is minor verbosity in the defaults and Next.js rationale sections, plus a deploy verification loop left to the external reference.

Suggestions

Tighten the Defaults & Assumptions and Next.js ssr/"Why?" sections into brief bullets to lift conciseness toward the lean anchor.

Add an inline sandbox/deploy validate→fix→retry checkpoint in the body (or a one-line pointer to the specific deployment.md validation step) so workflow clarity does not depend on an external file.

Collapse the repeated Next.js App Router vs Pages Router ssr explanations into a single compact comparison to reduce token weight.

Dimension	Reasoning	Score
Conciseness	Dense with executable code and routing tables and free of concept padding, but a few prose passages (the Defaults & Assumptions list and repeated Next.js ssr/"Why?" elaborations) could be tightened. Not 5 due to minor over-explanation; not 3 since no padding of concepts Claude already knows.	4 / 5
Actionability	Copy-paste-ready configuration code for every framework entry point (React, Next.js App/Pages, Vue, Angular, RN Expo/Bare, SvelteKit, Astro), specific commands ("npx ampx sandbox", exact npm install lines), and exact file paths cover the common cases fully.	5 / 5
Workflow Clarity	Quick Start routes by task type (Step 1→2→3) with a Gen2 detection checklist and explicit failure-mode warnings ("amplify_outputs.json must exist before the app can compile", "Auth UserPool not configured", silent-failure notes). Not 5 because the sandbox/deploy verification loop is delegated to deployment.md rather than given an inline validate→fix→retry checkpoint.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references: routing tables map each task/feature to a flat reference file, and all 14 referenced files exist and are appropriately split by feature and platform.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is exemplary: third-person voice, comprehensive concrete capabilities, explicit trigger and skip guidance, and strong distinctiveness boundaries. Every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full backend surface ("Build and deploy full-stack web and mobile apps", "Covers auth (Cognito), data (AppSync/DynamoDB), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock)"), with comprehensive named-service coverage.	5 / 5
Completeness	Explicitly answers both what ("Build and deploy full-stack... apps", backend coverage) and when ("Always use this skill for Amplify Gen2 topics", "TRIGGER when:") with concrete trigger phrases and SKIP boundary guidance.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms plus API names, package markers, and CLI commands ("user mentions Amplify Gen2", "amplify/ directory or amplify_outputs", "@aws-amplify packages", "defineBackend, defineAuth...", "npx ampx").	5 / 5
Distinctiveness Conflict Risk	Clear niche (Amplify Gen2) with an explicit SKIP clause distinguishing it from Gen1, standalone SAM/CDK, and direct Bedrock, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/web-and-mobile-development/aws-amplify/SKILL.md
Commit: d6ad2e4

Reviewed: about 2 hours 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.