Add antithesis-k8s-onboarding-assistance skill#142
Merged
Conversation
SeanTAllen
added
the
changelog - non-breaking
Contributor
Skill Context Report
|
Adds an interview-driven assistant skill for customers running on Kubernetes who are getting started with Antithesis. Bridges the gap between antithesis-research and antithesis-setup for k8s users — neither the customer's engineering team nor the Antithesis engagement team typically has full context on the customer's cluster setup, and the existing flow degenerates into a slow telephone game between them. The skill works collaboratively with the customer to figure out their SUT, dependencies, and stub strategy through horizontal and vertical minimization passes. Produces a structured ops-questions document the customer can paste into Slack, plus an escalation packet for the Antithesis engagement team when stuck. Output is a final report under antithesis/scratchbook/k8s-minimization.md plus working artifacts under antithesis/scratchbook/k8s-minimization-work/. Setup-side k8s support is a separate effort — until it lands, the skill's final report serves as a structured handoff packet for the Antithesis engagement team rather than a direct setup input. The skill is more experimental than its peers in this repo: unlike the others, it can't be dogfooded without a real customer engagement. The README NOTE block flags this and asks for aggressive feedback.
SeanTAllen
force-pushed
the
add-k8s-minimization-skill
branch
from
32a1791 to
984ee97
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A new skill for customers running on Kubernetes who are getting started with Antithesis. The skill works interactively with the customer (and the Antithesis engagement team) to figure out the test environment for their k8s-based system — what to keep, what to drop, what to stub — when neither side typically has full context on the cluster setup.
The skill produces a structured analysis report under
antithesis/scratchbook/k8s-minimization.mdplus working artifacts underantithesis/scratchbook/k8s-minimization-work/. K8s customers run it beforeantithesis-setup.This skill is more experimental than peer skills in this repo. Unlike research/setup/workload, we can't dogfood it without a real customer engagement, and the first such engagement will surface gaps we couldn't predict synthetically. The README has a NOTE block flagging this and asking for aggressive feedback.
Setup-side k8s support is a separate effort. Until it lands, the skill's final report serves as a structured handoff packet for the Antithesis engagement team rather than a direct setup input.