CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aws-sdk-java-v2-bedrock

Provides Amazon Bedrock patterns using AWS SDK for Java 2.x. Invokes foundation models (Claude, Llama, Titan), generates text and images, creates embeddings for RAG, streams real-time responses, and configures Spring Boot integration. Use when asking about Bedrock integration, Java SDK for AI models, AWS generative AI, Claude/Llama invocation, embeddings for RAG, or Spring Boot AI setup.

64

Quality

81%

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

The canonical home for this skill is giuseppe-trisciuoglio/developer-kit

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 delivers executable, production-oriented guidance with a validated workflow and well-organized one-level-deep references. Its main weaknesses are duplicated code blocks that inflate token cost and inlined advanced examples that would sit better in the existing reference files.

Suggestions

Consolidate the Claude payload into the shared createPayload() example and reference it from generateWithClaude and the Spring Boot service instead of repeating it three times; likewise drop the duplicated client-setup block in the Spring Boot section since Quick Start already shows it.

Move the full Spring Boot integration and streaming-with-retry examples to references/ (e.g., advanced-topics.md or bedrock-code-examples.md), keeping only a short snippet plus a pointer in SKILL.md.

Complete the code examples with the missing imports (org.json.JSONObject/JSONArray, InvokeModelResponse, PayloadPart) and define or reference the extractText helper used in the Spring Boot example so every snippet is copy-paste runnable.

DimensionReasoningScore

Conciseness

The body is almost entirely code with no concept-teaching padding, but it carries noticeable duplication: the Claude JSON payload appears three times (generateWithClaude, createPayload, Spring Boot generateText) and client setup appears twice (Quick Start and BedrockConfiguration). More than the 'minor trimming' of anchor 4, but not the padded verbosity of anchor 2.

3 / 5

Actionability

Complete Maven dependencies, working client setup, model IDs, and executable Java for every advertised use case. Minor gaps keep it below 5: several examples omit imports (JSONObject, InvokeModelResponse, PayloadPart) and the Spring Boot example calls an undefined 'extractText' helper.

4 / 5

Workflow Clarity

The 8-step Instructions sequence includes an explicit '**Validation Checkpoint**' and the streaming/retry examples implement real feedback loops (catch, exponential backoff, rethrow after max retries). Not 5 because the early setup steps ('Set up IAM roles', 'Request access... in AWS Console') lack concrete commands and validation appears at only a single checkpoint.

4 / 5

Progressive Disclosure

A clearly labeled References section lists six real files in references/ (all verified present), one level deep, each with a short description. Not 5 because substantial code (Spring Boot integration, streaming, backoff) is inlined in SKILL.md when reference files (bedrock-code-examples.md, aws-sdk-examples.md) already hold example content, leaving the overview heavier than it needs to be.

4 / 5

Total

15

/

20

Passed

Description

88%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 with concrete third-person capabilities and an explicit 'Use when' trigger clause covering the main use cases. Trigger coverage is good but omits a few natural terms (image generation, streaming, Titan), and some trigger phrases overlap closely related skills in the same domain.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions in third-person voice: 'Invokes foundation models (Claude, Llama, Titan), generates text and images, creates embeddings for RAG, streams real-time responses, and configures Spring Boot integration' — comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Both questions are explicitly answered: a clear 'what' (the concrete capability list) followed by an explicit 'Use when...' clause with concrete trigger phrases. Matches the anchor-5 example structure.

5 / 5

Trigger Term Quality

'Use when asking about Bedrock integration, Java SDK for AI models, AWS generative AI, Claude/Llama invocation, embeddings for RAG, or Spring Boot AI setup' provides good natural keyword coverage, but natural terms for image generation, streaming, and Titan are absent from the trigger clause. Not 5 because a few natural phrasings users would say are missing.

4 / 5

Distinctiveness Conflict Risk

The AWS SDK for Java 2.x + Bedrock niche is mostly distinct, but 'Claude/Llama invocation' and 'Spring Boot AI setup' triggers overlap with closely related skills in the same family (aws-sdk-java-v2-core, spring-boot-dependency-injection, langchain4j). Not 5 because minor overlap risk with these closely related skills exists.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

giuseppe-trisciuoglio/developer-kit

Path

plugins/developer-kit-java/skills/aws-sdk-java-v2-bedrock/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.