メニュー
Build and run a model server locally via Docker Compose, then test it with curl. Use when the engineer wants to test a model server locally before committing.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | local-test |
| description | Build and run a model server locally via Docker Compose, then test it with curl. Use when the engineer wants to test a model server locally before committing. |
| argument-hint | [service-name] |
| allowed-tools | ["Bash(docker *)","Bash(curl *)","Read"] |
Build, run, and test a model server locally.
.env file exists in the repo root with PATH_TO_<MODEL>_MODEL=/local/path/to/model.docker compose build <service>.docker compose up <service>.POST /v1/models/<model-name>:predict where <model-name> is the MODEL_NAME env var set for that service in docker-compose.yml. Check src/models/<service>/model_server/model.py for the expected input schema. Example for revert-risk language agnostic model: curl localhost:8080/v1/models/revertrisk-language-agnostic:predict -X POST -d '{"lang":"en","rev_id":12345}' -H "Content-type: application/json".Ctrl+C or docker compose down.platform: linux/amd64 to the service in docker-compose.yml.localhost:8080 by default. Check docker-compose.yml if the port is mapped differently. If :8080 is already in use, stop the other service or remap the port.https://analytics.wikimedia.org/published/wmf-ml-models/ and placed at the path referenced in .env.docker compose up -d <service>. Logs: docker compose logs <service>.$ARGUMENTS — the docker-compose service name (e.g., revertrisk-language-agnostic, articlequality, reference-need).
Triage Wikimedia ML inference-services incidents at a time T (now or past). TRIGGER on "investigate / triage / debug / post-mortem / what happened" when the subject is a LiftWing alert, ML-serve namespace, error spike, latency regression, or pod crash — including generic phrasing ("investigate this issue") when context (Phabricator task, pasted alert, log snippet) points at LiftWing, even with no alert string. Always trigger on: LiftWingServiceErrorRate, KubernetesDeploymentUnavailableReplicas, KubernetesPodCrashLooping; any namespace under revscoring*, revertrisk*, articletopic-outlink, or other ML-serve; clusters ml-serve-eqiad, ml-serve-codfw, ml-staging-codfw. SKIP only when modifying code without diagnosing a runtime incident. Pulls Prometheus via Grafana's anonymous datasource proxy; correlates with Gerrit merges in `inference-services` and `deployment-charts` (Phab IDs from `Bug:` footers). Read-only.
Analyze a model server's Python code and its deployment chart to identify performance bottlenecks and optimization opportunities for CPU and GPU (AMD MI300X, ROCm, vLLM) inference services on KServe. Use when you want to improve inference throughput or latency for a model.
Scaffold a new LiftWing ML service in operations/deployment-charts. Handles both adding to an existing namespace (append inference_services entry) and creating a brand-new namespace (full helmfile scaffold). Use when an engineer wants to deploy a new inference service for the first time.
Bump the Docker image tag for one or more LiftWing inference services in operations/deployment-charts after a new image is published by Jenkins. Use when a patch has merged in inference-services, PipelineBot has posted a new image tag on the Gerrit CL, and you need to update the corresponding values.yaml file(s) to deploy it.
Help pinpoint why a Wikimedia ML KServe/Knative InferenceService deployment is not working on ml-serve or ml-staging Kubernetes clusters.
Scaffold a new KServe model server from scratch — create the model.py, Blubber config, Docker Compose service, pipeline config, and CI wiring. Use when the engineer wants to add a new inference service model to this repo.