migrating-to-amazon-redshift

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

What it does

Guides an end-to-end data-warehouse migration to Amazon Redshift — discovery, schema/SQL/stored-procedure/macro/script conversion, data migration, validation, performance comparison, and reporting. Source-routed via `references/<source>/`; Teradata (Vantage) is the supported source; additional sources are added as their own `references/<source>/` sets. Text-only knowledge (no executable code) — the AI generates all execution at runtime. Applies when a user wants to migrate Teradata to Amazon Redshift, convert Teradata DDL/SQL/stored procedures/macros/BTEQ to Redshift/RSQL, or assess Teradata-to-Redshift migration complexity. Applies only to migrations targeting Amazon Redshift; migrations to other platforms (Snowflake, BigQuery, Databricks, etc.) are out of scope regardless of source. Does not cover general Redshift administration, performance tuning, or troubleshooting of existing Redshift clusters (no migration involved), or sources not listed under references/.

Install

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

npx skills add aws/agent-toolkit-for-aws --skill migrating-to-amazon-redshift

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/analytics-skills/migrating-to-amazon-redshift ~/.claude/skills/migrating-to-amazon-redshift

Safety box score

Grade C, moderate risk: 42 of 100 risk points, rated 2026-10-19. 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 a text-only migration guide, but it explicitly generates and runs shell/Python/AWS/Redshift/Teradata scripts at runtime to discover, extract, load, validate, and report on data. The main blast radius is data movement and target-side write/delete/truncate operations, plus exposure of credentials and S3-staged data during the migration workflow.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It says the AI will generate and run runtime scripts on the host shell, and that dependencies may be "pip install"-ed on demand (`SKILL.md`: "you (the AI) generate execution at runtime"; "pip install-ed on demand").
Network access	2 (moderate)	The workflow connects to Teradata, Redshift, S3, and AWS APIs, including `aws redshift get-cluster-credentials-with-iam` and `COPY ... FROM 's3://...'` (`bteq-to-rsql.md`, `data-migration-patterns.md`).
Filesystem reach	2 (moderate)	It writes resumable artifacts under `output/` and also recommends home-directory files like `~/.pgpass` and a git-ignored `.env` for local use (`SKILL.md`; `bteq-to-rsql.md`).
Secrets & credentials	2 (moderate)	It handles credentials via Secrets Manager/Parameter Store, local `.env` files or profiles, and `~/.pgpass`, and exports `PGUSER`/`PGPASSWORD` in an example runner (`SKILL.md`; `bteq-to-rsql.md`).
Privilege & persistence	0 (none)	No sudo, service registration, scheduled tasks, shell-startup edits, or OS-level privilege changes are requested; AWS permissions are used, but that is not local privilege escalation.
Instruction hijack surface	0 (none)	The files do not tell the agent to ignore safeguards, skip confirmation, or follow hidden remote instructions; they instead require explicit operator confirmation before production writes (`SKILL.md`).
Irreversible actions	3 (high)	It is an end-to-end migration workflow that can truncate and reload tables, copy data, and produce reports, so it can perform broad, potentially irreversible target-side changes (`data-migration-patterns.md`: `TRUNCATE <schema>.<table>; COPY ...`).
Transparency	0 (none)	The repository ships only Markdown guidance; there are no binaries, minified blobs, or hidden executable artifacts in the skill itself.

Before installing

Read `references/teradata/data-migration-patterns.md`: it uses `TRUNCATE` + `COPY`, so test only against a throwaway Redshift target first.
Check whether the host will create or read `~/.pgpass`, `.env`, or a co-located credentials file before installing.
Run a dry run in a sandbox AWS account with least-privilege IAM roles and an empty staging bucket.
Confirm the generated runner will install only pinned Python dependencies and will not echo credentials or PII.

Rated 2026-10-19 by an automated review of 14 files from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: skills/specialized-skills/analytics-skills/migrating-to-amazon-redshift/SKILL.md
Branch: main
Updated: 2026-09-19

redshift-guide — Amazon Redshift is NOT PostgreSQL — corrects PostgreSQL-derived LLM mistakes; covers Redshift-specific SQL, DDL, COPY/UNLOAD, system views, metadata discovery.
amazon-neptune — Provides authoritative guidance on Amazon Neptune Database and Neptune Analytics for graph, knowledge-graph.
aurora-dsql — Provisions and manages Aurora DSQL clusters, connects via psql or DSQL Connectors, manages schemas, runs queries, migrates from MySQL, diagnoses query plans.
dms-schema-conversion — Handles the full DMS Schema Conversion lifecycle including creating migration projects, converting database schemas to a target engine.
aws-database — Routes any task involving AWS databases — choosing, comparing, recommending, getting started with.
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.