- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill aws-lambda-durable-functions -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill aws-lambda-durable-functions -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill aws-lambda-durable-functions -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add awslabs/agent-plugins --skill aws-lambda-durable-functions -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/awslabs/agent-plugins/tree/HEAD/plugins/aws-serverless/skills/aws-lambda-durable-functions來自發布者
Build resilient multi-step applications and AI workflows that can execute for up to 1 year while maintaining reliable progress despite interruptions.
Before using AWS Lambda durable functions, verify:
AWS CLI is installed (2.33.22 or higher) and configured:
aws --version
aws sts get-caller-identity
Runtime environment is ready:
node --version)python --version. Note that currently only Lambda runtime environments 3.13+ come with the Durable Execution SDK pre-installed. 3.11 is the min supported Python version by the Durable SDK itself, however, you could use OCI to bring your own container image with your own Python runtime + Durable SDK.)Deployment capability exists (one of):
sam --version) 1.153.1 or highercdk --version) v2.237.1 or higherDefault: TypeScript
Override syntax:
When not specified, ALWAYS use TypeScript
Default: CDK
Override syntax:
When not specified, ALWAYS use CDK
For TypeScript/JavaScript:
npm install @aws/durable-execution-sdk-js
npm install --save-dev @aws/durable-execution-sdk-js-testing
For Python:
pip install aws-durable-execution-sdk-python
pip install aws-durable-execution-sdk-python-testing
Load the appropriate reference file based on what the user is working on:
TypeScript:
import { withDurableExecution, DurableContext } from '@aws/durable-execution-sdk-js';
export const handler = withDurableExecution(async (event, context: DurableContext) => {
const result = await context.step('process', async () => processData(event));
return result;
});
Python:
from aws_durable_execution_sdk_python import durable_execution, DurableContext
@durable_execution
def handler(event: dict, context: DurableContext) -> dict:
result = context.step(lambda _: process_data(event), name='process')
return result
runInChildContext to group operationscontext.logger (replay-aware)The Python SDK differs from TypeScript in several key areas:
@durable_step decorator + context.step(my_step(args)), or inline context.step(lambda _: ..., name='...'). Prefer the decorator for automatic step naming.context.wait(duration=Duration.from_seconds(n), name='...')ExecutionError (permanent), InvocationError (transient), CallbackError (callback failures)DurableFunctionTestRunner class directly - instantiate with handler, use context manager, call run(input=...)Durable functions require qualified ARNs (version, alias, or $LATEST):
# Valid
aws lambda invoke --function-name my-function:1 output.json
aws lambda invoke --function-name my-function:prod output.json
# Invalid - will fail
aws lambda invoke --function-name my-function output.json
Your Lambda execution role MUST have the AWSLambdaBasicDurableExecutionRolePolicy managed policy attached. This includes:
lambda:CheckpointDurableExecution - Persist execution statelambda:GetDurableExecutionState - Retrieve execution stateAdditional permissions needed for:
lambda:InvokeFunction on target function ARNslambda:SendDurableExecutionCallbackSuccess and lambda:SendDurableExecutionCallbackFailureWhen writing or reviewing durable function code, ALWAYS check for these replay model violations:
Date.now(), Math.random(), UUID generation, API calls, database queries must all be inside stepscontext.step(), context.wait(), or context.invoke() inside a step function — use context.runInChildContext() insteadcontext.logger for logging (it is replay-aware and deduplicates automatically)When implementing or modifying tests for durable functions, ALWAYS verify:
LocalDurableTestRunner for local testingWrite access is enabled by default. The plugin ships with --allow-write in .mcp.json, so the MCP server can create projects, generate IaC, and deploy on behalf of the user.
Access to sensitive data (like Lambda and API Gateway logs) is not enabled by default. To grant it, add --allow-sensitive-data-access to .mcp.json.
>
---name: aws-lambda-durable-functionsdescription: >---# plugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md常見問題
從發布者下載 plugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/awslabs/agent-plugins。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。