aws-cloudformation-bedrock
AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference profiles. Use when creating Bedrock agents with action groups, implementing RAG with knowledge bases, configuring vector stores, setting up content moderation guardrails, managing prompts, orchestrating workflows with flows, and configuring inference profiles for model optimization.
Install with Tessl CLI
npx tessl i github:giuseppe-trisciuoglio/developer-kit --skill aws-cloudformation-bedrock72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%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 an excellent skill description that clearly defines its scope at the intersection of AWS CloudFormation and Amazon Bedrock services. It provides comprehensive coverage of specific capabilities (agents, knowledge bases, guardrails, etc.) and includes explicit 'Use when' guidance with concrete trigger scenarios. The description uses proper third-person voice and includes natural keywords that AWS practitioners would use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creating Bedrock agents with action groups, implementing RAG with knowledge bases, configuring vector stores, setting up content moderation guardrails, managing prompts, orchestrating workflows with flows, and configuring inference profiles for model optimization.' | 3 / 3 |
Completeness | Clearly answers both what ('AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases...') and when ('Use when creating Bedrock agents with action groups, implementing RAG...') with explicit trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'CloudFormation', 'Bedrock', 'agents', 'knowledge bases', 'RAG', 'vector stores', 'guardrails', 'prompts', 'flows', 'inference profiles', 'action groups'. These are terms AWS users would naturally use when seeking this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically targets AWS CloudFormation + Amazon Bedrock intersection. The combination of 'CloudFormation patterns' with specific Bedrock resources creates a unique scope unlikely to conflict with general AWS or general AI skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, executable CloudFormation templates for Bedrock resources but suffers from severe verbosity. The content would be more effective as a concise overview with key patterns, delegating full templates to referenced files. The actionability is excellent but undermined by the sheer volume that makes it difficult to navigate.
Suggestions
Reduce the main file to ~100-150 lines with key patterns and snippets, moving complete templates to EXAMPLES.md
Add a deployment workflow section with explicit validation steps: 'aws cloudformation validate-template', 'aws cloudformation deploy --dry-run', and verification commands
Remove explanations of basic CloudFormation concepts (Parameters, Outputs, IAM roles) that Claude already understands
Restructure to show minimal viable examples inline with links to complete templates in referenced files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose at ~800+ lines with extensive boilerplate YAML that Claude can generate. It explains basic concepts like IAM roles, S3 buckets, and CloudFormation structure that Claude already knows. Much of this could be condensed to key patterns and references. | 1 / 3 |
Actionability | The YAML templates are complete, executable, and copy-paste ready. Each example includes all necessary resources (IAM roles, policies, dependencies) and uses proper CloudFormation syntax with realistic property values. | 3 / 3 |
Workflow Clarity | While the templates show resource dependencies through CloudFormation's implicit ordering, there's no explicit deployment workflow with validation steps. Missing guidance on how to validate templates before deployment, handle rollbacks, or verify successful resource creation. | 2 / 3 |
Progressive Disclosure | References REFERENCE.md and EXAMPLES.md at the end, but the main file contains massive inline examples that should be in those referenced files. The overview section is buried under hundreds of lines of YAML templates rather than providing a concise summary with pointers to details. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
62%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 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1262 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 10 / 16 Passed | |
- 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.