CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

75

Quality

92%

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

85%

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 clear routing, executable per-framework code, and a clean one-level-deep reference layout. Its only weakness is mild verbosity from restating a few points already conveyed in code comments.

Suggestions

Trim prose that restates code-comment guidance, e.g. the React Native pitfalls section repeats the 'react-native-get-random-values must be first' and AsyncStorage requirements already noted inline.

Consolidate the repeated Next.js ssr explanations (the App Router vs Pages Router { ssr: true } distinction is explained in the blockquote, the App Router subsection, and the Pages Router subsection).

Move the long per-framework entry-point configuration blocks into a dedicated reference (e.g. frontend-config.md) and keep SKILL.md to the routing table plus one representative example, reducing the body length.

DimensionReasoningScore

Conciseness

The body is information-dense and avoids explaining concepts Claude already knows, but at ~380 lines it restates some points (ssr guidance and React Native pitfalls are explained in prose after already being noted in code comments) and could be tightened.

2 / 3

Actionability

Provides copy-paste-ready, executable code per framework with exact entry-point files, exact install commands, and specific operational warnings (e.g., "react-native-get-random-values must be the FIRST import"), matching the score-3 anchor.

3 / 3

Workflow Clarity

Includes a routing table that sequences task identification to the correct reference, a Gen2 detection checklist, prerequisites, and validation-relevant warnings (sandbox must run before compile; wrong entry point causes silent failures), giving a clear sequence with checkpoints.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview with well-signaled, one-level-deep references organized by task type and platform; all 14 referenced files in references/ exist and are flat, with easy navigation via tables.

3 / 3

Total

11

/

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.

The description is specific, complete, and well-differentiated, naming concrete capabilities, explicit triggers, and skip conditions. It cleanly answers both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and resources ("Build and deploy full-stack web and mobile apps", "auth (Cognito), data (AppSync/DynamoDB), storage (S3), functions, APIs, and AI"), matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (build/deploy full-stack apps across auth/data/storage/functions/AI) and when via an explicit "TRIGGER when:" clause, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Covers natural terms users would say ("Amplify Gen2", "auth", "data", "storage", "functions", "npx ampx") plus framework names and API names (defineBackend, defineAuth, defineData), giving good coverage of likely trigger phrases.

3 / 3

Distinctiveness Conflict Risk

Scoped to Amplify Gen2 with distinct triggers and a "SKIP:" clause disambiguating Gen1, standalone SAM/CDK, and direct Bedrock, making conflict with adjacent skills unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aws/agent-toolkit-for-aws
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.