Skills Explorer Add Skills

aws-lambda-durable-functions

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

What it does

Builds resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like lambda durable functions, durable execution, workflow orchestration, state machines, retry/checkpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, reliable serverless applications, context.step, context.wait, context.invoke, context.runInChildContext, withDurableExecution, DurableContext, UnrecoverableInvocationError, durable-execution-sdk, qualified ARN invocation, and durable handler replay.

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-lambda-durable-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-lambda-durable-functions ~/.claude/skills/aws-lambda-durable-functions

Safety box score

Grade C, moderate risk: 26 of 100 risk points, rated 2026-10-20. 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 documentation and workflow guidance for AWS Lambda durable functions, including deployment, invocation, retries, callbacks, and troubleshooting. Its main risks are cloud-side side effects through AWS CLI/deployment commands and potential exposure of workflow data when pulling execution histories or logs.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution1 (low)It tells the agent to run commands like `npm install`, `pip install`, and `npx tsc --noEmit`, which execute local tooling and registry-sourced packages.
Network access2 (moderate)It uses AWS CLI calls (`aws lambda get-durable-execution-history`, `aws lambda invoke`, callback commands) that send requests to remote AWS services and can exchange callback data with external systems.
Filesystem reach1 (low)The skill expects creating and editing project files such as `src/handler.ts`, `tests/handler.test.ts`, and `infrastructure/template.yaml`, but it does not direct writes outside the project tree.
Secrets & credentials1 (low)It explicitly warns that checkpointed execution data and logs may contain sensitive data, e.g. `Do not return secrets, raw credentials, or PII from steps` and `execution data may contain sensitive information`.
Privilege & persistence0 (none)There is no `sudo`, service registration, shell startup modification, or other local privilege escalation in the skill files.
Instruction hijack surface0 (none)The docs contain imperative guidance, but they do not ask the agent to ignore safeguards, hide actions, or follow untrusted fetched instructions.
Irreversible actions2 (moderate)The skill is built around deploying and invoking durable workflows and includes side-effectful AWS actions like `cdk deploy`, `sam deploy --guided`, `aws lambda invoke`, and callback completion commands.
Transparency0 (none)All shipped files are plain markdown with readable commands and examples; there are no binaries, minified blobs, or opaque installers.

Before installing

Rated 2026-10-20 by an automated review of 12 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-lambda-durable-functions/SKILL.md
Branch
main
Updated
2026-09-19