processing-s3-uploads-with-step-functions

Deploy an event-driven workflow that routes S3 uploads to either Lambda or Fargate via Step Functions based on file size. Uses EventBridge to trigger a Step Functions state machine when objects are uploaded to S3. Small files are processed by Lambda, large files by a Fargate task. Includes VPC, ECR repository, ECS cluster, and scoped IAM roles. Trigger keywords: Step Functions, Fargate, Lambda, S3 event, EventBridge, ECS, ECR, file processing, workflow orchestration, serverless.

Quality

92%

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

85%

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

The content is highly actionable and well-structured with a clear sequenced workflow, explicit validation checkpoints, and appropriate one-level-deep reference delegation. Its only weakness is conciseness: the Security Considerations section duplicates several command blocks already shown in the procedures.

Suggestions

In the Security Considerations section, replace the verbatim egress-revocation, S3-encryption, and KMS-association command blocks with brief pointers back to Steps 2, 9, and 7 respectively to avoid token-eating duplication.

Consider consolidating the repeated security-egress narrative (Step 2 and Security Considerations) into a single canonical statement, referencing it from the other location.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and command-dense with no concept-explanation fluff, but the Security Considerations section repeats the Step 2 egress commands, the Step 9 S3-encryption command, and the Step 7 KMS log-group association verbatim. This 'mostly efficient but could be tightened' matches the score-2 anchor rather than the score-3 'every token earns its place'.	2 / 3
Actionability	Fully executable AWS CLI commands throughout — create-bucket, lambda create-function, docker build/tag/push, sed placeholder substitution, and stepfunctions create-state-machine — all copy-paste ready with exact placeholders. Matches the score-3 'fully executable, copy-paste ready' anchor rather than score-2 pseudocode.	3 / 3
Workflow Clarity	A clear 14-step sequence (Step 0–13) with explicit validation checkpoints (Step 6 get-function, Step 13 test upload + execution check) and error-recovery troubleshooting sections. Matches the score-3 anchor of clear sequence with explicit validation and feedback loops rather than score-2 'checkpoints missing or implicit'.	3 / 3
Progressive Disclosure	The overview delegates the two heaviest sub-procedures to one-level-deep references (Step 5 → references/iam-roles.md, Step 8 → references/ecs-task-definition.md) and keeps code assets in scripts/, all verified to exist and clearly signaled. Matches the score-3 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is strong: it specifies concrete actions and the full resource surface, provides an explicit keyword list covering natural user terms, answers both what and when, and occupies a distinctive niche. The only minor weakness is the trigger guidance being a bare keyword list rather than a natural-language 'Use when...' clause.

Dimension	Reasoning	Score
Specificity	Names many concrete actions and resources — 'routes S3 uploads to either Lambda or Fargate via Step Functions based on file size', 'Uses EventBridge to trigger a Step Functions state machine', and lists VPC, ECR, ECS, IAM roles. This matches the score-3 anchor of listing multiple specific concrete actions rather than the score-2 'some actions, not comprehensive'.	3 / 3
Completeness	Explicitly answers both what (deploys an event-driven S3→Step Functions→Lambda/Fargate routing workflow) and when (via the explicit Trigger keywords list serving as trigger guidance). Both what and when are explicitly present, matching the score-3 anchor rather than score-2 where 'when is missing or only implied'.	3 / 3
Trigger Term Quality	An explicit 'Trigger keywords:' list covers Step Functions, Fargate, Lambda, S3 event, EventBridge, ECS, ECR, file processing, workflow orchestration, and serverless — natural terms a user would say. Matches the score-3 anchor for good coverage rather than the score-2 'missing common variations'.	3 / 3
Distinctiveness Conflict Risk	The S3-upload-routing-by-file-size-to-Lambda-vs-Fargate-via-Step-Functions niche is highly specific with distinctive triggers unlikely to fire for a generic Lambda or S3 skill, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	12 / 12 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: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/serverless-skills/processing-s3-uploads-with-step-functions/SKILL.md
Commit: 222ce56

Reviewed: 3 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.