Conversation
ddericco
left a comment
There was a problem hiding this comment.
Domain SME review complete. One minor wording change and a suggestion re: documented values. Otherwise verified for accuracy, safety, and structure.
…REF values (v1.2.2)
ddericco
left a comment
There was a problem hiding this comment.
Domain SME review complete, recommended changes have been incorporated. Verified for accuracy, safety, and structure.
|
Thanks for the review, @ddericco. Both items are addressed in
Note on merge state: the branch-protection gate currently blocks because the existing approval was made with read-only permissions and the latest push requires a fresh approval from someone other than the last pusher. This needs an approving review from a maintainer with write access to clear. Happy to make any further adjustments. |
Add
aws-routingskillSummary
Adds
aws-routing, a read-only AWS routing subject-matter-expert skill for path selection, BGPtraffic engineering, and route evaluation across AWS networking services (Cloud WAN, Direct Connect,
Transit Gateway, VPC, VPN). It traces the end-to-end traffic path, applies the documented
route-evaluation order for each construct, flags non-deterministic path selection, and recommends
deterministic alternatives — grounded in public AWS documentation and field-proven patterns. It is
strictly advisory: analysis, recommendations, and read-only validation commands
(
describe-*/get-*/list-*) only, never mutating actions.What gap it fills
DevOps Agent can reason about individual routing facts but, in baseline testing, missed several
routing-specific determinants: the Cloud WAN CNE "deterministically random" final tiebreaker, the
DX-location-to-region association nuance, native Cloud WAN DX-attachment filtering behavior, and
TGW-to-VPN scaling paths. This skill encodes that route-evaluation logic so answers are deterministic
and correctly scoped.
What's included
Testing
reasoning trace confirms invocation). Baseline vs with-skill comparison captured.
aws-samples/sample-agent-skill-eval): Audit A (98/100, 0 critical / 0 warning),Functional A (0.972), Trigger 100% (14/14, standalone run). Run artifacts are regenerated locally;
the submission ships the spec-required
evals.json+eval_queries.json.Checklist
SKILL.mdhasversionandauthorin metadatanamefrontmatter matches directory name (aws-routing)descriptionstates what the skill does and when to activateREADME.mdincludes the non-production disclaimerCHANGELOG.mdpresentupstream/main