CtrlK
BlogDocsLog inGet started
Tessl Logo

migrate-to-msk

Helps migrate self-managed Apache Kafka workloads to Amazon MSK Express. Inventories the source cluster (from IaC files, Kafka CLI output, or manual input), assesses MSK Express compatibility across topology, Kafka version, configs, auth, and quotas, produces a target Express specification (instance type, broker count, monthly cost) by filling the AWS-published MSK Sizing/Pricing workbook, and guides migration execution using MSK Replicator. Applicable when the user mentions migrating Kafka, MSK, MSK Express, Kafka migration, analyzing Kafka infrastructure, moving to MSK, moving streaming platform to MSK, streaming migration, moving streaming workloads to AWS, MSK workload compatibility, choosing an MSK cluster type, or MSK Replicator. Prefer this skill to the managing-amazon-msk skill for migration questions.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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, actionable overview of a complex three-phase migration skill with clear sequencing, explicit gates, and clean one-level-deep progressive disclosure. Its main weakness is conciseness: the overview blockquote and guardrail lists duplicate content elaborated in the per-phase sections.

Suggestions

Collapse the phase-by-phase overview blockquote in Intent Routing §1 into a brief one-line-per-phase summary, since each phase is fully described in its own section later — this removes the main redundancy.

Consolidate the repeated guardrail/forbidden-behavior lists (e.g., the "Guardrails for this overview response" bullets overlap with the per-phase rules) into single canonical statements to tighten the body.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-explanation fluff Claude already knows, but it could be tightened: the overview blockquote in Intent Routing §1 re-describes all three phases that are then restated in each phase's own section, and the guardrail/forbidden-behavior lists are somewhat padded. Not a 1 because there is no generic library/background padding; not a 3 because of the redundant phase summaries and overall length.

2 / 3

Actionability

Concrete and executable at the level the body operates: named scripts ("uv run scripts/compatibility.py", "sizing.py --workbook <downloaded.xlsx>", "kafka-topics.sh, kafka-configs.sh, kafka-broker-api-versions.sh"), exact output paths, verbatim verdict strings, and a TLS setting ("EncryptionInTransit.ClientBroker = TLS"). Full command strings are deliberately one level deep in references, which is appropriate rather than a gap for this orchestration skill.

3 / 3

Workflow Clarity

Three phases are clearly sequenced with intent-to-phase routing and explicit checkpoints: a mandatory read-before-responding gate in discovery, "Do NOT proceed to Phase 2 without explicit customer confirmation", a "Do NOT pivot back into discovery" stop rule, and partial-data ADVISORY surfacing. Deeper validate→fix→retry loops live appropriately in references rather than being absent.

3 / 3

Progressive Disclosure

SKILL.md is a clear overview with well-signaled one-level-deep links to four reference files (discovery.md, assessment-compatibility.md, assessment-sizing.md, simulation.md), three scripts, and one asset, all verified to exist; reference cross-links are lateral siblings, not 2+-level nesting, and content is appropriately split (overview+rules inline, pseudocode/templates/flows in references, implementation in scripts).

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 is strong across all dimensions: it states concrete capabilities, lists natural trigger terms, explicitly covers both what and when, and explicitly disambiguates from a related skill. It uses third-person voice with no first/second-person slip.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Inventories the source cluster", "assesses MSK Express compatibility across topology, Kafka version, configs, auth, and quotas", "produces a target Express specification (instance type, broker count, monthly cost) by filling the AWS-published MSK Sizing/Pricing workbook", and "guides migration execution using MSK Replicator" — matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (the four-action inventory above) and when ("Applicable when the user mentions...") with an explicit trigger clause; it is not merely implied, so it clears the anchor for both what AND when.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered: "migrating Kafka, MSK, MSK Express, Kafka migration, analyzing Kafka infrastructure, moving to MSK, moving streaming platform to MSK, streaming migration, moving streaming workloads to AWS, MSK workload compatibility, choosing an MSK cluster type, or MSK Replicator" — these are phrases a user would actually say, not jargon.

3 / 3

Distinctiveness Conflict Risk

A clear niche (self-managed Kafka → MSK Express migration) with distinct triggers, plus an explicit disambiguation clause ("Prefer this skill to the managing-amazon-msk skill for migration questions") that actively reduces conflict with a sibling skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

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.