mlops-prototyping
Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.
OpenUI generative UI with Anthropic Claude SDK backend. Stream conversion to OpenAI NDJSON format.
OpenUI generative UI with Go (net/http) backend. Direct OpenAI API streaming via HTTP.
OpenUI generative UI with a Java Spring Boot (WebFlux) backend. Streams the OpenAI API directly via WebClient as SSE.
OpenUI generative UI with LangChain/LangGraph backend. Supports ChatOpenAI and ChatAnthropic.
OpenUI generative UI with OpenAI SDK backend. Streaming chat completions with gpt-5.5 (or any current OpenAI-compatible model).
OpenUI generative UI with Python FastAPI backend. OpenAI and Anthropic SDK variants.
OpenUI generative UI with Rust Axum backend. Async SSE streaming with reqwest and async-stream.
OpenUI generative UI with Vercel AI SDK. streamText, toUIMessageStreamResponse, and tools support.
用于需要把一个业务动作封装成Agent可调用工具、要设计动作执行前校验、重试和降级,用户出现“帮我定义Action契约”“这个动作失败后怎么办”或 action contract, pre-check, retry and fallback 等信号时调用。控制模式未定时可生成候选契约及模式选项,实际执行前落实授权与控制条件。
用于需要建设AI数据资产目录、训练数据、实时事实、规则和推理结果混在一起,用户出现“AI数据资产怎么分类”“训练和推理数据怎么分”或 AI data assets, training vs inference, provenance governance 等信号时调用。不适用于只需要普通数据仓库分层设计。
用于智能体作用已初步识别,需要把业务场景完整梳理成可建模、可开发和可验收的场景规格,用户出现“把这个场景完整详细梳理”“先把业务过程、判断和异常弄清楚”或 business scenario deep analysis, scenario specification 等信号时调用。不适用于只做本体适配初判或已经拥有完整场景规格。
用于已有逻辑本体和数据语义(包括明确隔离的候选版本),需要说明数据记录如何对应本体类、字段如何对应属性、关联如何对应对象关系,并生成可追溯实例,用户出现“把数据映射到本体类和属性”“生成本体实例”或 data-to-ontology mapping, ontology instantiation 等信号时调用。不适用于首次寻找真实系统中的表、字段和接口。
用于需要把模糊业务描述转成Agent可用模型、需要解释一个判断怎样落到系统动作,用户出现“帮我按事实事理行动拆解”“这个判断依据和动作怎么串起来”或 fact-reason-action, business loop, traceable action 等信号时调用。不适用于只需要解释术语或摘要文档。
用于需要解释Agent为什么得出某个业务判断、实时事实、业务规则和多个目标需要综合决策,用户出现“按事实事理目标分析”“这个决策依据是什么”或 fact-reason-goal, explainable decision, goal trade-off 等信号时调用。不适用于事实来源和任务目标均未明确。
Catalog captured:2026-11-21