菜单
Top-level model diagnostics router. Use when a request spans model lookup, checkpoint inspection, CI/debug, or observability and you need to choose/compose the right lower-level model and observability skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
End-to-end run-image classification with Gemini, including image fetch, prompt control, and JSON output. Use when you need parking or pull-over labels from a run_id.
Find a Gen2 MCAP from a run (or model-derived run), list topics, and extract topic/field values at a specific log time. Use when debugging run-level protobuf signals such as controller_state.
Fetch Buildkite job logs and extract failure lines for debugging CI jobs. Use when a user provides build/job ids or requests failure signal from Buildkite.
Use when forming Spark/SQL queries for Databricks parking evaluation - provides table schemas, PySpark patterns, joins, and filter patterns for PUDO/UNPUDO analysis
Work with Databricks notebooks using the REST API - list, read, modify, and write notebooks back to Databricks workspace
Inspect Flyte execution status and per-node/per-task log URIs from a Flyte Console execution URL. Use when a user asks for workflow status, step status, or logs for flyte.data.wayve.ai/dev executions.
| name | model-info-finder |
| description | Top-level model diagnostics router. Use when a request spans model lookup, checkpoint inspection, CI/debug, or observability and you need to choose/compose the right lower-level model and observability skills. |
This skill is the top node in a skill tree.
$model-catalogue-core: model id and checkpoint primitives.$obs-buildkite-jobs: Buildkite job log fetch + failure extraction.$obs-flyte-execution: Flyte execution status + step logs.$obs-datadog-logs: Datadog logs URL construction.$model-lookup-basic for nickname/author discovery.$model-deep-summary for one-model metadata (commit/licenses).$model-checkpoint-inspector for checkpoint licenses/runs.$modelci-shadowgym-debug for ModelCI, Buildkite, Eval Studio, Shadow Gym troubleshooting.Use one composite skill when the request is narrow:
$model-lookup-basic$model-checkpoint-inspectorCompose skills when request crosses domains:
$modelci-shadowgym-debug + $obs-flyte-execution$obs-buildkite-jobs + $obs-datadog-logsLegacy scripts remain in this folder, but prefer routed skills:
lookup_by_nickname.shlookup_by_author.shdeep_model_summary.shcheckpoint_licenses.shcheckpoint_runs.shmodelci_evalstudio_shadowgym.shmodel_catalogue_api_helpers.shPrefer the focused skills for new work.