CtrlK
BlogDocsLog inGet started
Tessl Logo

transitgateway

Configures AWS Transit Gateway: creating a hub and attaching VPCs, segmenting traffic with route tables, centralizing egress and inspection through a hub (appliances or a Gateway Load Balancer endpoint), forcing east-west traffic between VPCs through AWS Network Firewall, connecting on-premises networks over the transit-gateway side of a Site-to-Site VPN or Direct Connect attachment (including ECMP to aggregate bandwidth across multiple VPN tunnels), peering transit gateways across Regions, migrating from a VPC peering mesh, and routing IP multicast. Applicable when connecting many VPCs through one router, isolating environments, forcing VPC-to-VPC traffic through a central Network Firewall, reaching on-premises over the hub, linking Regions, or moving off a peering mesh. Not applicable for single-VPC routing, VPC peering between two VPCs (vpcpeering skill), Direct Connect gateway or virtual interface setup (directconnect skill), or Route 53 DNS work.

69

Quality

85%

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

78%Weight 40%Scale 1-5

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

A well-architected router skill: a clean task-dispatch table, decision-dense routing notes, and concrete security MUSTs, with detail correctly pushed to one-level-deep reference files that all exist. The main weakness is mild Overview redundancy with the description and validation being delegated to references rather than surfaced in the body.

Suggestions

Trim the Overview capability list so it does not restate the description verbatim; keep only the 'router' framing and the read-before-acting instruction.

Surface a brief post-change verification checkpoint in the body (e.g. 'after any route table change, confirm associations/propagations and check Flow Logs') given the documented blast radius, rather than relying solely on the references for validation.

DimensionReasoningScore

Conciseness

The body is dense and decision-focused, but the Overview paragraph largely restates the capability list already in the description (e.g. 'Covers building the hub and attaching VPCs, segmenting traffic with route tables, centralizing egress and inspection ...'), a minor redundancy that could be trimmed — fitting the 'efficient; minor instances of over-explanation' anchor.

4 / 5

Actionability

As an instruction-only router skill it carries no inline code, but it gives concrete actionable guidance: a task-dispatch table mapping each goal to a specific reference file plus firm decision rules ('GWLB is the recommended approach for new designs', 'Appliance mode is required for stateful cross-Availability-Zone inspection'). Per the instruction-only scoring note, absent code is not penalized when guidance is actionable, so this sits at mostly-executable with minor gaps.

4 / 5

Workflow Clarity

A clear sequence is established — 'Read the matching reference in full before acting, then follow its constraints and steps' — with a task table as the entry point and pre-build routing notes as guardrails (e.g. 'Decide segmentation before you build'). Detailed per-task validation lives in the references rather than the body, leaving minor validation gaps at the router level.

4 / 5

Progressive Disclosure

Clean overview that dispatches to 8 reference files via a well-signaled task table with markdown links, all of which exist in references/ and are described as self-contained; references are exactly one level deep and easy to navigate, matching the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

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

A strong, third-person description that enumerates concrete capabilities, gives explicit 'use when' and 'not for' triggers, and disambiguates from neighboring skills. The only gap is a couple of common natural phrasings ('hub and spoke', 'TGW') that would round out the trigger coverage.

Suggestions

Add the common natural phrase 'hub and spoke' (and the 'TGW' abbreviation) to the trigger phrasing so users who describe the architecture that way land on this skill.

Consider trimming the long parenthetical on ECMP inside the capability list to keep the description tighter without losing the trigger.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'creating a hub and attaching VPCs, segmenting traffic with route tables, centralizing egress and inspection ... forcing east-west traffic ... through AWS Network Firewall, ... peering transit gateways across Regions, migrating from a VPC peering mesh, and routing IP multicast' — comprehensive coverage, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

Explicitly answers both 'what' (the long capability list) and 'when' via the 'Applicable when ...' clause with concrete trigger phrases, plus boundary guidance in 'Not applicable for ...', matching the anchor for clearly and explicitly answering both what and when.

5 / 5

Trigger Term Quality

Strong natural triggers — 'connecting many VPCs through one router', 'isolating environments', 'reaching on-premises over the hub', 'moving off a peering mesh' — but a few common phrases users say are missing, notably 'hub and spoke' and the 'TGW' abbreviation, so it sits at good-but-not-comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Regional TGW hub routing) and it explicitly disambiguates from sibling skills — 'VPC peering between two VPCs (vpcpeering skill), Direct Connect gateway or virtual interface setup (directconnect skill)' — minimizing conflict risk.

5 / 5

Total

19

/

20

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.