CtrlK
BlogDocsLog inGet started
Tessl Logo

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, 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/.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, source-routed overview with a clear phased workflow, strong security and validation checkpoints, and detail appropriately split into verified one-level-deep references; its main weakness is some repetition of the 'knowledge not code' framing and scope restatement.

Suggestions

Consolidate the 'knowledge over shipped code / no executable code' rationale, which currently appears in the intro, the principle line, and the frontmatter — state it once and reference it elsewhere.

Drop scope/out-of-scope restatements already covered by the frontmatter description to avoid duplication between the description and the body.

Trim the philosophical 'Do not look for a pyproject, a tools package, an orchestrator engine, or shipped scripts' sentence; the single principle line already conveys the same point.

DimensionReasoningScore

Conciseness

The body is information-dense with migration-specific operational knowledge Claude does not already know, but repeats the 'knowledge over shipped code / no executable code' framing across the intro and principle line and restates scope already present in the frontmatter, so it is mostly efficient yet could be tightened rather than fully lean.

2 / 3

Actionability

It gives concrete directives — apply conversion-rules.md directly, prefer WRITE_NOS + teradatasql, pin exact dependency versions, stage in encrypted S3, load via COPY IAM_ROLE, scope the role policy to the staging prefix with aws:SourceAccount/aws:SourceArn/sts:ExternalId, enable CloudTrail and audit logging — so per the instruction-only carve-out the absence of shipped code is not penalized.

3 / 3

Workflow Clarity

Six ordered phases each feeding result/ to the next, a dedicated Validation phase, restartable data migration, a state.md progress cursor, and a non-production checkpoint with 'never point write-path at production without explicit operator confirmation' form a clear sequence with explicit validation, so it is not capped at 2.

3 / 3

Progressive Disclosure

An organized overview body points to 13 one-level-deep reference files (all verified present in references/teradata/) via a labeled References table, with no nested references, matching the clear-overview-with-well-signaled-references anchor.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states concrete capabilities, natural trigger terms, explicit use-conditions, and strong scope boundaries that prevent mis-triggering, using proper third-person voice.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions — 'discovery, schema/SQL/stored-procedure/macro/script conversion, data migration, validation, performance comparison, and reporting' — matching the score-3 anchor of listing several specific actions rather than naming only a domain.

3 / 3

Completeness

Answers both 'what' (the end-to-end migration phases) and 'when' via the explicit trigger clause 'Applies when a user wants to migrate Teradata to Amazon Redshift...', so it is not capped at 2 for a missing or implied 'when'.

3 / 3

Trigger Term Quality

Phrases like 'migrate Teradata to Amazon Redshift, convert Teradata DDL/SQL/stored procedures/macros/BTEQ to Redshift/RSQL, or assess Teradata-to-Redshift migration complexity' are exactly what a user would say, giving good natural-term coverage rather than only some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

A narrow Teradata-to-Redshift niche plus explicit out-of-scope boundaries ('migrations to other platforms... out of scope', 'Does not cover general Redshift administration...') make it unlikely to trigger for the wrong skill; voice is third-person ('Guides...') so no specificity penalty applies.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 31 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
aws/agent-toolkit-for-aws
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.