菜单
Connect to SageMaker Managed MLflow (mlflow-app or mlflow-tracking-server ARN) as an MLflow backend, then hand off to the other MLflow skills. Triggers on a SageMaker MLflow ARN (arn:aws:sagemaker:...:mlflow-app/... or arn:aws:sagemaker:...:mlflow-tracking-server/...) or "SageMaker Managed MLflow".
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mlflow/skills --skill sagemaker-mlflow命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | sagemaker-mlflow |
| description | Connect to SageMaker Managed MLflow (mlflow-app or mlflow-tracking-server ARN) as an MLflow backend, then hand off to the other MLflow skills. Triggers on a SageMaker MLflow ARN (arn:aws:sagemaker:...:mlflow-app/... or arn:aws:sagemaker:...:mlflow-tracking-server/...) or "SageMaker Managed MLflow". |
Establishes the connection to SageMaker Managed MLflow (the sagemaker-mlflow plugin + an
ARN tracking URI + AWS credentials), then hands off to the requested MLflow skill
(instrumenting-with-mlflow-tracing, agent-evaluation, retrieving-mlflow-traces,
querying-mlflow-metrics, etc.), which inherit the connection via MLFLOW_TRACKING_URI.
Requires Python >= 3.10 (mlflow >= 3.8). Validate and report the fix — never auto-install the plugin or acquire credentials (mirrors the repo's Databricks pattern).
python --version -> must be 3.10+. If older, STOP and tell the user.aws configure / SSO, or an IAM role). If
they error (ExpiredToken / no creds), STOP and ask the user to configure them.
(scripts/verify_connection.py also checks this, via boto3.)pip install sagemaker-mlflow
Required even if MLFLOW_TRACKING_URI is already an ARN — without it,
mlflow.set_tracking_uri() fails with UnsupportedModelRegistryStoreURIException.
MLFLOW_TRACKING_URI is set to
arn:aws:sagemaker:...), use it as-is.python scripts/discover_arns.py
mlflow-app and mlflow-tracking-server ARNs work; the ARN is also
shown on the resource's detail page in the SageMaker Studio console.Then export it (the ARN is region-bound — a cross-region ARN will not authenticate):
export MLFLOW_TRACKING_URI="<arn>" # mlflow-app/<id> or mlflow-tracking-server/<name>
export AWS_DEFAULT_REGION="<region>" # AWS credentials resolved via the default chain (SigV4)
python scripts/verify_connection.py "$MLFLOW_TRACKING_URI"
Checks all three prerequisites (plugin / credentials / ARN connectivity) and exits non-zero with a remediation hint on the first failure. Do not proceed until it passes.
After the connection verifies, hand off to the requested MLflow skill — it inherits the
connected environment via MLFLOW_TRACKING_URI.
UnsupportedModelRegistryStoreURIException — the sagemaker-mlflow plugin is not
installed; pip install sagemaker-mlflow, then re-run scripts/verify_connection.py.AccessDenied / 403 — credentials are missing/expired, or the principal lacks MLflow
permissions on the ARN. Check that credentials resolve, grant sagemaker-mlflow /
sagemaker permissions, and confirm the ARN region matches AWS_DEFAULT_REGION.Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart tutorials and initial integration. If an experiment ID is available, it should be supplied as input to help determine the use case. Use when the user asks to get started with MLflow, set up tracking, add observability, or integrate MLflow into their project. Triggers on "get started with MLflow", "set up MLflow", "onboard to MLflow", "add MLflow to my project", "how do I use MLflow".
Drives a disciplined explore → plan → implement → verify loop for changing an AI agent's behavior with confidence — whether fixing a reported failure or introducing a new requirement, business rule, or policy. Grounds the diagnosis in MLflow traces, codifies the desired behavior as a regression test suite (`mlflow.genai.evaluate` assertions in `@mlflow.test` pytest tests), and iterates the agent — not the test — until green, resisting quick system-prompt patches when the real fix is upstream (missing tool, retrieval source, or capability). Use whenever the user wants to fix or change how an agent behaves — e.g. "fix this issue in my agent", "this answer is wrong", "the agent is hallucinating", "improve my agent based on this trace", "make the agent do X instead of Y", "I want the agent to lead with/prioritize/recommend X", "new business rule: the agent should X", "always/never do X", "change the agent's default behavior" — or when you are debugging an agent's behavior mid-loop and reaching for source code and
Instruments Python and TypeScript code with MLflow Tracing for observability. Must be loaded when setting up tracing as part of any workflow including agent evaluation. Triggers on adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, tracing specific frameworks (LangGraph, LangChain, OpenAI, Gemini, DSPy, CrewAI, AutoGen), or when another skill references tracing setup. Examples - "How do I add tracing?", "Instrument my agent", "Trace my LangChain app", "Set up tracing for evaluation"
基于 SOC 职业分类
