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.
84
77%
Does it follow best practices?
Impact
100%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/bedrock/SKILL.mdQuality
Discovery
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 description with explicit 'Use when...' guidance and good trigger term coverage for the AWS Bedrock domain. The main weakness is that the capabilities could be more concrete (e.g., specific API operations, model types supported) rather than high-level categories like 'building AI applications'.
Suggestions
Add more specific concrete actions like 'invoke Claude/Titan models via API', 'manage model provisioned throughput', or 'configure guardrails' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AWS Bedrock) and lists some actions (invoking models, building AI applications, creating embeddings, configuring access, implementing RAG), but these are somewhat high-level rather than concrete specific operations like API calls or configuration steps. | 2 / 3 |
Completeness | Clearly answers both what (AWS Bedrock foundation models for generative AI) and when (explicit 'Use when...' clause listing five specific trigger scenarios: invoking models, building AI apps, embeddings, model access, RAG patterns). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'foundation models', 'generative AI', 'embeddings', 'model access', 'RAG patterns'. These are terms developers working with AWS Bedrock would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche targeting AWS Bedrock specifically, with distinct triggers like 'foundation models', 'Bedrock', and 'RAG patterns' that wouldn't conflict with general coding or other cloud service skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable AWS Bedrock skill with excellent executable code examples and good troubleshooting coverage. However, it's verbose for a skill file - it includes explanatory content Claude already knows and could benefit from splitting detailed references into separate files. The workflow for getting started (enabling model access, verifying permissions, then invoking) could be more explicitly sequenced with validation checkpoints.
Suggestions
Remove or significantly trim the 'Core Concepts' section - Claude knows what foundation models are and which providers offer them
Add an explicit 'Getting Started Workflow' with validation steps: 1) Check model access status, 2) Request access if needed, 3) Verify IAM permissions, 4) Test with simple invocation
Move CLI Reference tables and detailed troubleshooting to separate files (e.g., CLI_REFERENCE.md, TROUBLESHOOTING.md) and link from main skill
Remove the Table of Contents - it adds tokens without value for Claude's navigation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary content like the Table of Contents (Claude can navigate without it), explanatory text about what foundation models are, and the model listing table that Claude likely knows. The core concepts section could be trimmed significantly. | 2 / 3 |
Actionability | Excellent executable code examples throughout - CLI commands and Python code are copy-paste ready with proper imports, error handling patterns, and realistic usage examples. The streaming, embeddings, and conversation examples are complete and functional. | 3 / 3 |
Workflow Clarity | Individual operations are clear, but multi-step workflows lack explicit validation checkpoints. For example, the model access workflow doesn't clearly sequence: check access -> request if needed -> verify -> then invoke. The retry pattern is good but validation steps before invocation are implicit. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in one large file (~300 lines). The CLI reference tables, troubleshooting section, and detailed code examples could be split into separate reference files with the main skill providing a concise overview and links. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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
5df6da7
- 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.