5500 个 · 按相关度排序
Set up machine learning training and inference on NVIDIA DGX Spark. Get guidance on choosing containers and packages, resolving CUDA compatibility errors, and checking that PyTorch can access the GPU before starting a workload.
中文简介正在准备中。当前显示英语简介。
Create and manage subscriptions that receive Google Workspace event notifications. Stream events as NDJSON, a format with one JSON record per line, and inspect, renew, reactivate, or delete subscriptions through the available commands.
中文简介正在准备中。当前显示英语简介。
Automate D2lbrightspace operations through Rube MCP, a connection for agent tools. The skill guides agents through discovering supported operations, checking the service connection, and executing tasks with current input formats and shared workflow sessions.
中文简介正在准备中。当前显示英语简介。
Build and publish a browser demo for a supplied LoRA, a model adaptation for image or video tasks. Tailor the Gradio interface to its inputs and follow the model’s recommended settings on Hugging Face Spaces.
中文简介正在准备中。当前显示英语简介。
Prepare an isolated local environment for manually testing DevSpace changes. Copy existing settings and state into the current checkout, build interface assets, start the development server, and refresh the test snapshot when needed.
中文简介正在准备中。当前显示英语简介。
Agent fallback for CBaseEntity_DispatchSpawn-decompiles (auto-generated, category: func). Locate CBaseEntity::DispatchSpawn in the CS2 server module via IDA Pro MCP and emit a fresh, minimal-unique artifact. The deterministic preprocessor could not resolve this symbol on the current gamever - your job is the re-sign. Trigger: CBaseEntity_DispatchSpawn-decompiles, CBaseEntity::DispatchSpawn
中文简介正在准备中。当前显示原文说明。
Renew or reactivate Google Workspace Events subscriptions, the settings used to receive events. Update one subscription by name or renew those nearing expiration within a chosen time window, with cron available for recurring runs.
中文简介正在准备中。当前显示英语简介。
Plan and manage Cloud Spanner databases on Google Cloud, design tables and primary keys, write SQL and client code, and investigate slow queries using database statistics to identify resource-intensive operations.
中文简介正在准备中。当前显示英语简介。
Prepare new hires' onboarding from Google Workspace group records and documented role standards. Plan accounts and memberships, invite hires to Slack channels, and create first-week Linear checklists, while holding Workspace access changes for human approval.
中文简介正在准备中。当前显示英语简介。
Run empirical and causal analyses in Python with StatsPAI, from stating assumptions to estimating effects and checking how results change under alternative choices. Produce diagnostic figures, regression tables, and replication bundles for economics, public health, or machine learning studies.
中文简介正在准备中。当前显示英语简介。
UI stack, build, and test conventions for NV oOS React SPA addons (toolkit-shell, chat-spa, schedule-anything-spa, saas-controller) — three sanctioned build patterns plus the standalone Pro SPA Vite app (examples/nvoos-pro-spa-vite), dual-React guard, headless component rules, NDS tokens, Tailwind v4, @xyflow/react v12, vitest/jsdom gotchas, the full-JS-rebuild map, and the TS-shadows-JS webpack gotcha. Use when building or modifying SPA addon UI, writing SPA JS tests, upgrading SPA deps, or rebuilding JS for packaging.
中文简介正在准备中。当前显示原文说明。
Organize existing ChatGPT Pages and Spaces around the work readers need to do. The skill reviews page structure, moves pages, consolidates duplicate content, and improves navigation while preserving distinct requirements, historical context, and relevant layout details.
中文简介正在准备中。当前显示英语简介。
Update existing ChatGPT Pages or a Space using new meetings and source material. The skill reconciles plans, tasks, and reference information, combines duplicates, preserves human edits and dated records, and reports changes and coverage gaps.
中文简介正在准备中。当前显示英语简介。
Send plain text messages to a specified Google Chat space using the gws command line tool. Use it for team updates and announcements, with guidance on finding space identifiers and confirming messages before sending.
中文简介正在准备中。当前显示英语简介。
Manage Google Chat spaces, the places where conversations happen, and their messages through the gws command-line tool. Create or update spaces, add members, send messages, and upload or download attachments.
中文简介正在准备中。当前显示英语简介。
Receive selected Google Workspace events and stream them as NDJSON, a format with one JSON record per line. Choose event types, use an existing subscription, or save each event to a separate file.
中文简介正在准备中。当前显示英语简介。
Plan and configure a shared GKE cluster for multiple teams or environments. Set up namespaces, team permissions, resource limits, and network separation, then use labels and GKE cost allocation to track spending by team.
中文简介正在准备中。当前显示英语简介。
Look up Google user profiles and search the Workspace directory through gog. Retrieve your own profile, a profile by ID, or user relationship information, with JSON output available for further processing.
中文简介正在准备中。当前显示英语简介。
Find workspaces on remote nodes, inspect their details, browse folders, and read or write files. Supports text files and binary content, such as images, through base64 encoding, a text representation of binary data.
中文简介正在准备中。当前显示英语简介。
Tune Megatron Bridge training for MoE models, which route tokens to specialized experts, by overlapping expert communication with computation. Check dispatcher requirements, avoid conflicting settings, and compare steady training performance while changing one overlap setting at a time.
中文简介正在准备中。当前显示英语简介。
Build custom Python data sources for Apache Spark using the PySpark DataSource API — batch and streaming readers/writers for external systems. Use this skill whenever someone wants to connect Spark to an external system (database, API, message queue, custom protocol), build a Spark connector or plugin in Python, implement a DataSourceReader or DataSourceWriter, pull data from or push data to a system via Spark, or work with the PySpark DataSource API in any way. Even if they just say "read from X in Spark" or "write DataFrame to Y" and there's no native connector, this skill applies.
中文简介正在准备中。当前显示原文说明。
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
中文简介正在准备中。当前显示原文说明。
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
中文简介正在准备中。当前显示原文说明。
Plan memory use and monitor long training jobs on NVIDIA DGX Spark. It guides troubleshooting for out-of-memory failures, tracks temperature and power alongside training logs, and helps assess competition between training and inference workloads.
中文简介正在准备中。当前显示英语简介。