dms-schema-conversion

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: aws, database, migration, schema, sql.

What it does

Handles the full DMS Schema Conversion lifecycle including creating migration projects, converting database schemas to a target engine, running compatibility assessments, navigating metadata trees, exporting converted DDL to S3, applying schema changes to a target database, and converting SQL statements between database engines. Applies when migrating database schemas between heterogeneous engines using AWS DMS Schema Conversion.

Install

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

npx skills add aws/agent-toolkit-for-aws --skill dms-schema-conversion

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/migration-and-modernization-skills/dms-schema-conversion ~/.claude/skills/dms-schema-conversion

Safety box score

Grade D, elevated risk: 58 of 100 risk points, rated 2026-10-17. 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 drives AWS DMS Schema Conversion end-to-end: it can create and manage migration projects, IAM roles, S3 buckets, data providers, and can export or apply converted DDL to a target database. The main risks are broad AWS-account changes, live target database modifications, and destructive cleanup of DMS resources; it also depends on fetching remote AWS documentation before acting.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	3 (high)	The skill repeatedly requires shell/AWS CLI execution such as `aws dms ...`, `aws s3 cp ...`, `aws iam create-role`, and waiter/polling loops, so it can run many commands on the user's behalf.
Network access	2 (moderate)	It sends requests to AWS DMS, IAM, S3, Secrets Manager, and RDS, and it also says `You MUST fetch and read any linked documentation before acting on it`, which adds outbound web traffic.
Filesystem reach	1 (low)	Its local file access is mostly bounded to the working directory, e.g. `aws s3 cp ... ./Summary.csv` and `./exported_target.sql`, with guidance to delete those working copies afterward.
Secrets & credentials	2 (moderate)	It asks for Secrets Manager secret ARNs for source/target credentials and creates a dummy secret for virtual targets, but it does not instruct the agent to read or print plaintext passwords.
Privilege & persistence	2 (moderate)	The setup and cleanup flows create/attach IAM roles and policies and modify S3 bucket settings, so it can change account-level permissions and storage configuration.
Instruction hijack surface	1 (low)	The global constraint `You MUST fetch and read any linked documentation before acting on it` makes behavior depend on remote content, which broadens the prompt-injection surface even though the links are official AWS docs.
Irreversible actions	3 (high)	It can apply converted schema to a live target with `start-metadata-model-export-to-target` and can also delete migration projects and related DMS resources during cleanup, both of which are high-impact actions.
Transparency	0 (none)	All shipped files are readable markdown references; there are no binaries, embedded installers, or decoded-at-runtime payloads.

Before installing

Confirm you are okay with a skill that can create/delete AWS DMS resources, IAM roles, and S3 buckets in your account.
If you might use "Apply to target," test it in a non-production migration project first.
Read the cleanup section and decide whether deleting the migration project and related DMS resources is acceptable.
Make sure the correct AWS region and account will be used before letting the agent run.

Rated 2026-10-17 by an automated review of 6 files from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: skills/specialized-skills/migration-and-modernization-skills/dms-schema-conversion/SKILL.md
Branch: main
Updated: 2026-09-19

aurora-dsql — Provisions and manages Aurora DSQL clusters, connects via psql or DSQL Connectors, manages schemas, runs queries, migrates from MySQL, diagnoses query plans.
amazon-neptune — Provides authoritative guidance on Amazon Neptune Database and Neptune Analytics for graph, knowledge-graph.
migrating-to-amazon-redshift — Guides an end-to-end data-warehouse migration to Amazon Redshift — discovery, schema/SQL/stored-procedure/macro/script conversion, data migration, validation.
creating-data-lake-table — Create managed Iceberg tables using Amazon S3 Tables (s3tables API namespace) with automatic compaction and snapshot management.
ingesting-into-data-lake — Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift.
launch-with-aws — Migrates vibe-coded web applications to AWS.