Skills Explorer Add Skills

aws-step-functions

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: automation, aws, orchestration, serverless, workflow.

What it does

Authors and edits AWS Step Functions state machines: writes Amazon States Language (ASL) in JSONata, and chooses and structures state types (Task, Choice, Map, Parallel, Pass, Wait, Succeed, Fail). Covers ASL syntax, JSONata data transformation and variables, Retry/Catch error handling, service integrations (.sync, waitForTaskToken callbacks), Distributed Map for large-scale S3/CSV processing, saga/compensation patterns, Standard vs Express workflow choice, TestState API unit testing, and migrating state machines from JSONPath to JSONata. Use when the user is building, authoring, debugging, or migrating a Step Functions state machine or ASL definition, or orchestrating multi-step workflows with branching, retries, or human-approval callbacks, even if they don't say 'Step Functions.' Do NOT use for general Lambda function code, API Gateway, EventBridge wiring, or SAM/CDK application packaging.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add aws/agent-toolkit-for-aws --skill aws-step-functions

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/skills/specialized-skills/serverless-skills/aws-step-functions ~/.claude/skills/aws-step-functions

Safety box score

Grade B, low risk: 19 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is plain-text guidance plus ASL example files for AWS Step Functions; it does not ship runnable code, installers, or local scripts. The main blast radius is on AWS: copied workflows can send SQS/SNS messages, start child executions, and handle approval callbacks, and the examples include sensitive task-token handling.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)No native scripts or code execution are shipped; the repository is markdown plus `.asl.json` examples only.
Network access1 (low)Network use is limited to documented AWS API/CLI calls such as `aws stepfunctions test-state` and service integrations like `sqs:sendMessage` and `sns:publish`, and the docs say to ask before making AWS API calls.
Filesystem reach1 (low)The skill targets state-machine definition files saved as `.asl.json` in the project workspace; it does not touch dotfiles, system paths, or other outside-project locations.
Secrets & credentials1 (low)It explicitly treats `.waitForTaskToken` tokens as credentials and discusses AWS credentials/Secrets Manager, but it does not request pasted passwords or read local secret stores.
Privilege & persistence0 (none)There is no sudo, service installation, shell-profile editing, or other local privilege change in the shipped files.
Instruction hijack surface0 (none)No file tells the agent to ignore instructions, hide behavior, or follow remote content; the text is straightforward Step Functions guidance.
Irreversible actions2 (moderate)The examples can send messages, publish notifications, and start executions (`sqs:sendMessage`, `sns:publish`, `states:startExecution`), which are real AWS-side actions even though they are template definitions.
Transparency0 (none)All reviewed files are readable text; there are no binaries, base64 blobs, or downloaded installers.

Before installing

Rated 2026-10-19 by an automated review of 16 files from the skill's repository.

Source

Repository
aws/agent-toolkit-for-aws (all skills from this repository)
Path
skills/specialized-skills/serverless-skills/aws-step-functions/SKILL.md
Branch
main
Updated
2026-09-19