aws

AWS cloud services expert for EC2, S3, Lambda, IAM, and AWS CLI

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./crates/openfang-skills/bundled/aws/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 body is a well-organized, lean set of AWS best-practice guidance with good trigger specificity and no unnecessary concept explanations, but it lacks a sequenced workflow with validation feedback loops and most guidance is directive rather than copy-paste executable.

Suggestions

Add a short ordered pre-flight/verification workflow with explicit checkpoints (e.g., confirm identity/region -> dry-run changes -> validate with CloudTrail/Config) to improve workflow clarity for destructive operations.

Tighten generic bullets (e.g., "Keep functions small and focused") and the intro sentence to remove guidance Claude already knows, raising conciseness.

Add one or two complete, copy-paste-ready command or CloudFormation/CDK snippets for the most common tasks to lift actionability.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet guidance that avoids explaining concepts Claude already knows, but the intro sentence and generic bullets like "Keep functions small and focused" and "check the pricing calculator first" could be tightened to fully earn a 3.	2 / 3
Actionability	It includes some concrete specifics (inline commands `aws sts get-caller-identity`, instance families `c`/`r`/`t3-m*`, CIDR `0.0.0.0/0`) but the bulk is directive best-practice rather than complete, copy-paste-ready code or commands.	2 / 3
Workflow Clarity	Content is organized into clear sections with one useful pre-flight validation check (confirm region/account before changes), but it is topic-organized reference guidance rather than a sequenced workflow with feedback loops, capping at 2 for destructive AWS operations.	2 / 3
Progressive Disclosure	The skill is under 50 lines, requires no external references (no bundle files present), and is well-organized into clear sections, which per the judging guidelines lets progressive disclosure score 3 on well-organized sections alone.	3 / 3
	Total	9 / 12 Passed

Description

72%

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

The description is specific and well-targeted with strong natural trigger terms and low conflict risk, but it omits any explicit "Use when..." trigger guidance and states a role rather than concrete actions.

Suggestions

Add a "Use when..." clause naming the situations that should trigger this skill, e.g. "Use when working with AWS services like EC2, S3, Lambda, or IAM, or when running AWS CLI commands."

Replace the role phrasing "expert" with concrete actions, e.g. "Architect, deploy, and manage AWS services..." to strengthen the specificity of capabilities.

Dimension	Reasoning	Score
Specificity	The description names the AWS domain and concrete services ("EC2, S3, Lambda, IAM, and AWS CLI") but states a role ("expert") rather than listing concrete actions, so it falls short of the multiple-specific-actions anchor at 3 yet is more concrete than the vague anchor at 1.	2 / 3
Completeness	It answers "what" (AWS expert for listed services) but lacks any "Use when..." clause or explicit trigger guidance, which per the judging guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	The service names "EC2", "S3", "Lambda", "IAM", and "AWS CLI" are precisely the natural terms a user would say when they need this skill, giving good coverage of natural trigger keywords.	3 / 3
Distinctiveness Conflict Risk	It carves a clear AWS niche with named services as distinct triggers, making it unlikely to fire for non-AWS work or conflict with unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: RightNow-AI/openfang
Path: crates/openfang-skills/bundled/aws/SKILL.md
Commit: acf2587

Reviewed: about 7 hours 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.