- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add awslabs/agent-plugins --skill aws-step-functions -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add awslabs/agent-plugins --skill aws-step-functions -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add awslabs/agent-plugins --skill aws-step-functions -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add awslabs/agent-plugins --skill aws-step-functions -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/awslabs/agent-plugins/tree/HEAD/plugins/aws-serverless/skills/aws-step-functions来自发布者
AWS Step Functions uses Amazon States Language (ASL) to define state machines as JSON. With AWS Step Functions, you can create workflows, also called State machines, to build distributed applications, automate processes, orchestrate microservices, and create data and machine learning pipelines.
This skill provides comprehensive guidance for writing state machines in ASL, covering:
$states reserved variableAssignLoad the appropriate reference file based on what the user is working on:
Choose Standard for: payment processing, order fulfillment, compliance workflows, anything that must never execute twice.
Choose Express for: IoT data ingestion, streaming transformations, mobile backends, high-throughput short-lived processing.
JSONata is the modern, preferred way to reference and transform data in ASL. It replaces the five JSONPath I/O fields (InputPath, Parameters, ResultSelector, ResultPath, OutputPath) with just two: Arguments (inputs) and Output.
Enable at the top level to apply to all states:
{ "QueryLanguage": "JSONata", "StartAt": "...", "States": {...} }
Or per-state to migrate from JSONPath incrementally:
{ "Type": "Task", "QueryLanguage": "JSONata", ... }
JSONPath is still supported and is the default if QueryLanguage is omitted — existing state machines do not need to be migrated.
"QueryLanguage": "JSONata" at the top level for new state machines unless the user wants to use JSONPathOutput minimal — only include what the state immediately after the current state needsAssign to store variables needed in later states instead of threading it through Output$states.input to reference original state inputAssign and Output are evaluated in parallel — variable assignments in Assign are NOT available in Output of the same state$data.nonExistentField throws States.QueryEvaluationError$states.context.Execution.Input to access the original workflow input from any state.asl.json extension when working outside the consolearn:aws:states:::lambda:invoke) over the SDK integrationStates.QueryEvaluationError — JSONata expression failed. Check for type errors, undefined fields, or out-of-range values.$ or $$ at the top level of a JSONata expression — use $states.input instead.{% %} delimiters around JSONata expressions — the string will be treated as a literal.Assign and expecting them in Output of the same state — new values only take effect in the next state.Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS
---name: aws-step-functionsdescription: Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States…---# plugins/aws-serverless/skills/aws-step-functions/SKILL.md概览
Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.
常见问题
从发布者处下载 plugins/aws-serverless/skills/aws-step-functions/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/awslabs/agent-plugins。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。