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.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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.

A thorough, highly actionable reference skill with executable code and CLI examples, well-structured troubleshooting, and clear navigation. It is slightly verbose in places and, given its length, could benefit from splitting bulk reference material into one-level-deep bundle files.

Suggestions

Trim the intro paragraph that restates the description, and consider moving the full IAM policy JSON and CLI reference tables into references/ files to tighten the core SKILL.md.

Add a short end-to-end 'first invocation' checklist (enable access -> submit use case form -> invoke -> verify stop_reason) with an explicit validation checkpoint to strengthen workflow clarity.

Split the CLI Reference and/or Troubleshooting sections into separate one-level-deep reference files linked from the body to improve progressive disclosure for this large skill.

Dimension	Reasoning	Score
Conciseness	Dense with actionable specifics and no padding about concepts Claude already knows, but the intro paragraph restates the description and the large inlined IAM JSON/CLI tables could be trimmed or split, keeping it just below the lean anchor 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready boto3 and AWS CLI examples covering the common cases (invoke, stream, embeddings, conversation, list/check models, token counting) with real model IDs and parameters.	5 / 5
Workflow Clarity	Patterns and troubleshooting sections are clearly sequenced with cause/debug/solution structure and a retry feedback loop, but as a reference catalog it lacks a single end-to-end validated workflow with explicit checkpoints throughout.	4 / 5
Progressive Disclosure	Well-organized with a Table of Contents and clear section headers, and external AWS docs are cleanly listed in References; however the ~497-line single file inlines bulk CLI reference tables and IAM policy content that a large reference skill could split into separate bundle files.	4 / 5
	Total	17 / 20 Passed

Description

92%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, third-person description that names the domain, lists several concrete capabilities, and provides an explicit 'Use when' trigger clause with natural keywords. The only minor gap is trigger-term synonym coverage, which keeps trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns' — giving comprehensive coverage of the Bedrock surface area.	5 / 5
Completeness	Explicitly answers both 'what' (AWS Bedrock foundation models for generative AI) and 'when' ('Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural terms (foundation models, embeddings, model access, RAG), but lacks some synonyms/variations users might say and the API-service domain has no file extensions to anchor on, stopping short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear Bedrock-specific niche with distinct triggers (foundation models, embeddings, model access, RAG); minimal overlap risk with adjacent AWS or AI skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: itsmostafa/aws-agent-skills
Path: skills/bedrock/SKILL.md
Commit: e786d25

Reviewed: 2 days 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.