923 个 · 按相关度排序
Prepare high-quality datasets for LLM fine-tuning with filtering, deduplication, augmentation, and RLHF data formatting. Activate on: fine-tuning data, training data curation, RLHF dataset, data quality filtering, SFT dataset. NOT for: model training infrastructure (ai-engineer), prompt engineering without fine-tuning (prompt-engineer).
中文简介正在准备中。当前显示原文说明。
使用hf命令查找、下载和上传Hugging Face Hub上的模型与数据集，并管理仓库、运行环境和本地缓存，支持通过JSON输出实现自动化。
Use PyTDC to discover therapeutic machine-learning datasets, create task-appropriate training and test splits, and evaluate predictions against curated benchmarks. Also score selected molecules with supported scoring functions, with explicit download plans and bounded outputs.
中文简介正在准备中。当前显示英语简介。
Find scientific datasets, AI models, methodology posts, and interactive demos through the Hugging Science catalog. Compare candidates for a research task and verify their licenses, input formats, access requirements, and supported ways to run them.
中文简介正在准备中。当前显示英语简介。
Draft or review manuscript statements explaining where data and code can be accessed. Organize repository choices, access restrictions, identifiers, and dataset citations, and check metadata that helps others find and reuse the research data.
中文简介正在准备中。当前显示英语简介。
Create shareable links that open specific Arize resources, including traces, datasets, and evaluators. Use IDs from logs or exported data, with suitable time ranges, to direct teammates to the relevant view.
中文简介正在准备中。当前显示英语简介。
Manage BigQuery datasets, tables, views, and jobs, and run SQL queries for basic data analysis. Provides setup examples and references for data ingestion, command-line operations, client libraries, access permissions, and infrastructure configuration.
中文简介正在准备中。当前显示英语简介。
Evaluate AI models and agents on Google Cloud using test datasets and scoring criteria. Generate simulated user scenarios, analyze failures, and compare results across changes to guide improvements to prompts and code.
中文简介正在准备中。当前显示英语简介。
Build or review quality control workflows for single-cell and single-nucleus RNA sequencing data. Select filters from observed data, detect doublets, assign cell types, and create UMAP plots that summarize cell relationships, while recording analysis decisions and outputs.
中文简介正在准备中。当前显示英语简介。
Query ProteomeXchange through its PROXI API to inspect datasets, libraries, proteins, peptide forms, and spectra. Receive concise summaries focused on a dataset or identifier, and save complete responses when more detail is needed.
中文简介正在准备中。当前显示英语简介。
Find and assess datasets for a research question. Dispatches Explorer agents to search across data source categories, then Explorer-Critic to stress-test each candidate. Produces a ranked list with feasibility grades. Make sure to use this skill whenever the user wants to identify or evaluate data sources — not to search for papers or run analysis. Triggers include: "find data", "what data should I use", "find a dataset for this", "where can I get data on X", "assess datasets", "what datasets exist for", "help me find data", "is there data on this", "what are my data options", "I need data for this project", or any request to locate empirical data sources for a research question.
中文简介正在准备中。当前显示原文说明。
Render a GeoJSON dataset on an interactive Leaflet map in the Views section of a dataset's showcase. Installs react-leaflet and a Map component, then renders the map for the chosen dataset. Use when a dataset's data is geographic and a map view is needed alongside the showcase's default metadata and download.
中文简介正在准备中。当前显示原文说明。
Designs complete single-cell research plans from a user-provided biomedical direction. Always use this skill whenever a user wants to design, scope, or structure a single-cell study — including disease-focused, mechanism-focused, biomarker-focused, translational, perturbation-inspired, or validation-aware projects. It should define the research question, choose the best-fit study pattern, recommend sample grouping logic, suggest reference datasets as examples only, specify the core analysis modules, propose a validation ladder, and output four workload configurations (Lite / Standard / Advanced / Publication+). Never fabricate datasets, sample metadata, accession numbers, cohort availability, cell-type labels, external validation resources, or literature references. Always include the mandatory Dataset Disclaimer immediately before any workflow section that mentions datasets or public resources.
中文简介正在准备中。当前显示原文说明。
Designs complete integrated research plans for bulk transcriptomics, proteomics, metabolomics, and related omics from a user-provided biomedical direction. Always use this skill whenever a user wants to design, scope, or structure a bulk multi-omics or single-omics-plus-clinical study — including disease-focused, mechanism-focused, biomarker-focused, stratification-oriented, or translational projects. It should define the research question, choose the best-fit study pattern, recommend example datasets as reference candidates only, specify the core analysis modules and method choices, propose a validation ladder, and output four workload configurations (Lite / Standard / Advanced / Publication+). Never fabricate datasets, accession numbers, sample counts, metadata completeness, cohort availability, assay coverage, literature references, PMIDs, DOIs, or validation status. Always include the mandatory Dataset Disclaimer immediately before any workflow section that mentions datasets or public resources.
中文简介正在准备中。当前显示原文说明。
This skill should be used when user asks to "upload my model to Ultralytics Platform", "push this run to the platform", "upload a dataset to platform", "download a dataset from platform", "search platform datasets", "start cloud training", "train on platform GPUs", "export a model on platform", "deploy a model endpoint", "run Moondream on Platform", "auto-annotate a Platform dataset", "run hosted AI inference", "why is my run not showing on platform", or mentions platform.ultralytics.com, ul:// URIs, ultralytics-platform, or ULTRALYTICS_API_KEY.
中文简介正在准备中。当前显示原文说明。
Expert knowledge for Azure Open Datasets development including limits & quotas. Use when handling non-Spark dataset downloads, throttling behavior, quota limits, retry logic, or rate-limit workarounds, and other Azure Open Datasets related development tasks. Not for Azure Data Explorer (use azure-data-explorer), Azure Synapse Analytics (use azure-synapse-analytics), Azure Databricks (use azure-databricks), Azure Machine Learning (use azure-machine-learning).
中文简介正在准备中。当前显示原文说明。
Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection. Triggers on phrases like "dataset bias", "stratified sample", "class imbalance", "data distribution", "fairness analysis", or "ethical review".
中文简介正在准备中。当前显示原文说明。
使用 ArkCLI 创建、校验、查询、更新、删除、版本化和下载 Dataset。用户提到 Dataset、数据集、ds-*、dsv-*、训练集/验证集复用、数据格式校验或把 Dataset 接入精调任务时使用。
中文简介正在准备中。当前显示原文说明。
Switch this session to another Cognee dataset, or back to the previous one, so later saves and recalls use it. Takes a dataset name (created if new) or lists writable datasets to pick from; syncs this session first.
中文简介正在准备中。当前显示原文说明。
Configure CRM Analytics (formerly Einstein Analytics) app sharing, dataset-level permissions, row-level security predicates, sharing inheritance, and license assignment. Trigger keywords: CRM Analytics security, row-level security predicate, dataset permissions, analytics sharing inheritance, Analytics Plus license. NOT for OWD and sharing rules — use admin/sharing-and-visibility. NOT for predicate design across many datasets — use architect/analytics-security-architecture.
中文简介正在准备中。当前显示原文说明。
Adaption AI SDK for synthetic data augmentation and dataset adaptation. Use when building data pipelines with the Adaption Python SDK, uploading datasets (local files, Hugging Face, Kaggle), running augmentation/adaptation jobs, configuring brand controls (hallucination mitigation, safety categories, length), recipe specifications (reasoning traces, deduplication, preference pairs, prompt rephrase), evaluating dataset quality, downloading results, or any workflow involving `pip install adaption`, `from adaption import Adaption`, Adaptive Data, or the adaptionlabs.ai API. Also trigger when the user mentions synthetic data generation for fine-tuning, dataset augmentation pipelines, DPO preference pair generation, or grounding-based hallucination reduction on training data.
中文简介正在准备中。当前显示原文说明。
Interactively build a Narrative identity graph workflow from one or more first-party datasets and (optionally) third-party data sources. Confirms each input dataset is mapped to the Rosetta Stone graph edge attribute (mapping it via /generate-rosetta-stone-mappings if not), then composes and submits a workflow that unions every edge source and labels connected components. Use when: "build an identity graph", "generate an identity graph", "create an identity graph", "stitch these datasets into a graph", "make a graph workflow", "label connected components on these datasets", "I want a person graph / household graph / device graph". (narrative-identity)
中文简介正在准备中。当前显示原文说明。
Generate, evaluate, and improve Rosetta Stone attribute mappings for a Narrative dataset. Use when: "map this dataset to Rosetta Stone", "suggest normalized attributes for dataset N", "evaluate the mappings on dataset N", "why is this mapping low confidence", "fix this expression", "improve this NQL mapping expression". (narrative-common)
中文简介正在准备中。当前显示原文说明。
Write, validate, and (optionally) execute an NQL query against a Narrative dataset. Drafts the query from the user's question, runs `narrative_nql_validate` until it compiles, explains the query in plain English, and only runs it on explicit approval (or when invoked with `--run`). Use when: "write an NQL query for X", "query this dataset", "validate this NQL", "run NQL against dataset <id>", "how many rows match Y", "show me the top N records from <dataset>". (narrative-common)
中文简介正在准备中。当前显示原文说明。