aws-sdk-js-v3-usage

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: api, cloud, javascript, sdk, validation.

What it does

AWS SDK for JavaScript v3 development patterns. Use when writing JavaScript or TypeScript code that uses AWS services via @aws-sdk/* packages (aws-sdk-js-v3), or when asked about schemas, runtime validation, serialization, or code generation in the context of the JS/TS AWS SDK.

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-sdk-js-v3-usage

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/plugins/aws-core/skills/aws-sdk-js-v3-usage ~/.claude/skills/aws-sdk-js-v3-usage

Safety box score

Grade B, low risk: 25 of 100 risk points, rated 2026-10-14. 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 only: it ships markdown guidance and code snippets for AWS SDK for JavaScript v3, with no executable scripts. The main risks come from the patterns it teaches—reading local AWS credentials, making outbound AWS/API calls, and performing cloud-side publish/upload actions if the generated code is run.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No scripts or binaries are shipped; the repo is markdown reference material with code examples only.
Network access	2 (moderate)	The skill centers on `client.send(...)`, presigned URLs, multipart uploads, waiters, and credential providers that contact AWS/STS/IMDS, so generated code can make outbound requests and transfer data.
Filesystem reach	1 (low)	It shows local file access such as `fs.readFileSync("./layer_content.zip")` and references `~/.aws/credentials` / `~/.aws/config`, but it does not automate broad file writes or deletion.
Secrets & credentials	2 (moderate)	`fromEnv()` uses `AWS_ACCESS_KEY_ID` / `AWS_SECRET_ACCESS_KEY`, and `fromIni()` reads `~/.aws/credentials` / `~/.aws/config`, so following the examples can consume local AWS secrets and profiles.
Privilege & persistence	0 (none)	There is no sudo use, global install, service registration, or shell/OS configuration change in the shipped files.
Instruction hijack surface	0 (none)	No prompt-injection content is present; the files do not instruct the agent to ignore rules, hide actions, or fetch remote instructions.
Irreversible actions	1 (low)	Some examples perform remote mutations like `publishLayerVersion`, `Upload.done()`, and `waitUntil*`, but the skill itself is reference material rather than an automation workflow.
Transparency	0 (none)	All files are readable markdown; there are no binaries, minified blobs, or runtime-decoded code.

Before installing

Read `references/credentials.md` first and decide whether the agent should ever see your `~/.aws/*` profiles or `AWS_ACCESS_KEY_ID`-style env vars.
Run any generated code in a throwaway AWS account or sandbox profile before letting it use real credentials.
Inspect `references/lambda.md` and `references/s3.md` for `publishLayerVersion`, `Upload`, and `waitUntil*` before allowing the agent to execute them.

Rated 2026-10-14 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: plugins/aws-core/skills/aws-sdk-js-v3-usage/SKILL.md
Branch: main
Collection: aws-core
Updated: 2026-09-19

aws-sdk-python-usage — AWS SDK for Python (boto3/botocore) development patterns. You MUST use this skill when writing Python code that uses AWS services via boto3 or botocore.
aws-sdk-swift-usage — AWS SDK for Swift development patterns. Use when writing Swift code that uses AWS services via aws-sdk-swift package.
amazon-bedrock — Builds generative AI applications on Amazon Bedrock.
aws-cloudformation — Authors, validates, and troubleshoots AWS CloudFormation templates.
aws-database — Routes any task involving AWS databases — choosing, comparing, recommending, getting started with.
aws-iam — Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits.