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

73%

Does it follow best practices?

Impact

100%

1.03x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/bedrock/SKILL.md

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability with concrete, executable code examples covering the major Bedrock patterns. However, it's overly long and monolithic—cramming CLI references, multiple full code examples, best practices, and troubleshooting into a single file without progressive disclosure. Some sections explain concepts Claude already knows (what foundation models are, basic model descriptions) which wastes token budget.

Suggestions

Split CLI reference tables, troubleshooting, and advanced patterns (conversation history, streaming) into separate referenced files to improve progressive disclosure and reduce the main file's token footprint.

Remove the Core Concepts section or reduce it to a single line—Claude already knows what foundation models, embeddings, and inference types are.

Add an explicit setup workflow with validation: 1) Check model access → 2) Verify IAM permissions → 3) Test invocation → 4) Validate response structure, to improve workflow clarity for first-time Bedrock setup.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary content Claude already knows (listing what foundation models are, explaining what embeddings are, the inference types table). The code examples are useful but the overall document is quite long (~300 lines) with sections like Core Concepts that add little value for Claude. The CLI reference tables and best practices bullet points are somewhat padded.	2 / 3
Actionability	The skill provides fully executable, copy-paste ready code examples for all major patterns: invoking models via CLI and boto3, streaming, embeddings, conversation history, and retry logic. CLI commands include specific flags and jq parsing. The IAM policy JSON is concrete and usable.	3 / 3
Workflow Clarity	The skill presents individual patterns clearly but lacks explicit multi-step workflows with validation checkpoints. For example, there's no workflow for 'setting up Bedrock from scratch' (enable access → verify → invoke → validate response). The troubleshooting section helps but the retry pattern is the only feedback loop present.	2 / 3
Progressive Disclosure	The entire skill is a monolithic document with no bundle files or references to supplementary files. The CLI reference tables, all code examples, troubleshooting, and best practices are all inline. Content like the full Conversation class, CLI reference tables, and detailed troubleshooting sections could be split into separate files with clear navigation from the main skill.	1 / 3
	Total	8 / 12 Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a well-structured skill description that clearly identifies its domain (AWS Bedrock) and provides explicit trigger guidance via a 'Use when...' clause with multiple relevant scenarios. The specificity of capabilities could be slightly improved by listing more concrete actions (e.g., 'invoke InvokeModel API', 'set up knowledge bases'), but the trigger terms and completeness are strong.

Dimension	Reasoning	Score
Specificity	Names the domain (AWS Bedrock foundation models) and some actions (invoking models, building AI applications, creating embeddings, configuring model access, implementing RAG patterns), but these are somewhat high-level rather than deeply concrete operations like specific API calls or configuration steps.	2 / 3
Completeness	Clearly answers both 'what' (AWS Bedrock foundation models for generative AI) and 'when' with an explicit 'Use when...' clause listing five distinct trigger scenarios (invoking models, building AI apps, creating embeddings, configuring access, implementing RAG).	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'AWS Bedrock', 'foundation models', 'generative AI', 'embeddings', 'model access', 'RAG patterns'. These cover the main terms a user working with Bedrock would naturally use.	3 / 3
Distinctiveness Conflict Risk	The combination of 'AWS Bedrock' with specific triggers like 'foundation models', 'embeddings', and 'RAG patterns' creates a clear niche. While 'building AI applications' is broad, the AWS Bedrock anchor makes it unlikely to conflict with non-Bedrock skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: itsmostafa/aws-agent-skills
Commit: 4ab904a

Reviewed: about 1 month 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.