bedrock

AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.

1.03x

Quality

77%

Does it follow best practices?

Impact

100%

1.03x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/bedrock/SKILL.md

Evaluation results

100%

AI Model Comparison Tool

Multi-model invocation patterns

Criteria

Without context

With context

Claude model ID

100%

Claude anthropic_version

100%

Claude response parsing

100%

Titan Text model ID

100%

Titan request format

100%

Titan response parsing

100%

Llama model ID

100%

Llama prompt format

100%

boto3 client service name

100%

contentType and accept headers

100%

Retry on ThrottlingException

100%

No retry on ValidationException

100%

Customer Support Chat Assistant

Streaming conversation with Converse API

Criteria

Without context

With context

Uses Converse API

100%

Converse message format

100%

System prompt as list

100%

inferenceConfig dict

100%

Conversation history maintained

100%

Streaming invocation

100%

Stream chunk handling

100%

boto3 runtime client

100%

Claude model used

100%

Two-turn demo

100%

Semantic Search for Documentation Snippets

Embedding generation and vector similarity

Criteria

Without context

With context

Titan embed model ID

100%

inputText field name

100%

dimensions parameter

100%

normalize parameter

100%

Embedding response parsing

100%

boto3 runtime client

100%

contentType and accept

100%

README model explanation

100%

Cosine similarity implemented

100%

Repository: itsmostafa/aws-agent-skills
Commit: 5df6da7

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

AI Model Comparison Tool Customer Support Chat Assistant Semantic Search for Documentation Snippets

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.