查找技能

为Cloud Worker创建并选择预装工具的镜像，验证启动时间和会话运行状态。验证失败时恢复原镜像选择，并在获得明确批准后删除旧镜像。

• 创建预装所需工具的镜像
• 比较镜像变更前后的启动时间
• 确认新镜像上的会话正常运行

使用远程环境或Docker测试安装、服务集成和实际操作，根据代码可信程度选择环境，并完成故障排查、结果检查及测试后的资源清理。

• 在干净环境中测试软件包安装
• 验证与真实服务的集成
• 检查macOS、Windows及WSL2行为

Build or review Java Spring Boot backends using examples for web APIs, separate application layers, and database access. Covers input validation, error handling, caching, background processing, and logging to guide maintainable implementations.

中文简介正在准备中。当前显示英语简介。

• Designing web APIs and separating application layers
• Reviewing database access and transactions
• Adding input validation and centralized error handling

通过具体实现示例设计或审查Java的Quarkus服务，涵盖REST API分层、Panache数据访问、Camel消息路由、RabbitMQ集成及异步处理。

• 划分REST API的职责
• 集成Camel与RabbitMQ
• 审查Panache数据保存逻辑

Develop and refactor Quarkus 3.x LTS services by writing tests first. Covers API responses, event handling, and asynchronous operations, with unit and integration tests plus coverage checks to show how much code is tested.

中文简介正在准备中。当前显示英语简介。

• Adding REST endpoints with tests first
• Reproducing bugs before fixing them
• Testing Apache Camel routes and event handling

帮助设计和实现 TypeScript 后端中的 Prisma 数据库代码，通过具体示例检查查询、批量更新、迁移和连接管理中的常见问题。

• 设计 Prisma 模型及关联
• 检查查询与分页逻辑
• 排查事务和批量更新问题

Set up GPU servers on Lambda Labs for machine learning training and inference. Follow workflows for SSH access, persistent storage, Python API operations, and distributed training that spreads work across multiple GPUs or servers.

中文简介正在准备中。当前显示英语简介。

• Set up a GPU server for long training jobs
• Fine-tune a large language model across multiple GPUs
• Keep datasets and checkpoints between sessions

Prepare LLM training datasets with NeMo Curator by removing duplicates, filtering low-quality content, and redacting personal information. The skill also covers image, video, and audio curation, including GPU processing and distributed workflows.

中文简介正在准备中。当前显示英语简介。

• Clean web-scraped text for LLM training
• Remove exact, near, and meaning-based duplicates
• Remove or replace personal information in text

Guides implementation and maintenance of Claude applications using language-specific references and official SDKs, the libraries used to call the API. Covers tool integration, streaming responses, model migration, cost reviews, prompt audits, and evaluation workflows.

中文简介正在准备中。当前显示英语简介。

• Adding Claude API calls to an application
• Building an agent that uses custom tools
• Migrating existing Claude integrations to another model

Migrate code and API calls from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Update platform-specific model identifiers and address reported prompt behavior issues, such as excessive tool use or unnecessary code complexity.

中文简介正在准备中。当前显示英语简介。

• Updating model identifiers in existing code
• Migrating API settings for a specific platform
• Adjusting prompts that trigger excessive tool use

Publish a folder of static HTML and assets to the configured Paperclip S3/CloudFront host. Validate the folder before upload, obtain a persistent public URL, and update an existing page from its original publishing directory.

中文简介正在准备中。当前显示英语简介。

• Sharing a static report through a persistent URL
• Publishing an HTML prototype or viewer
• Checking a site's structure and URL before publishing

Set up RuView sensing nodes by building and flashing ESP32 firmware, configuring WiFi and the receiving address, and checking serial logs. Diagnose missing CSI streams, the WiFi signal measurements sent by sensing nodes.

中文简介正在准备中。当前显示英语简介。

• Setting up a new RuView sensing node
• Reflashing firmware for an 8 MB or 4 MB ESP32-S3
• Configuring WiFi and the receiving server

Get RuView running with a Docker demo using simulated WiFi signal data, source checks, or live sensing with supported hardware. Choose a starting path based on available equipment and open a working sensing dashboard.

中文简介正在准备中。当前显示英语简介。

• Try the dashboard without sensing hardware
• Explore the API or develop the interface using simulated data
• Check the Rust build and Python verification

Set up an ESP32-S3/C6 sensing node for RuView by choosing firmware, checking and flashing binaries, and configuring WiFi and capture settings. Use boot logs to confirm CSI, measurements of the WiFi channel, is being captured.

中文简介正在准备中。当前显示英语简介。

• Choosing firmware for an ESP32 board
• Flashing firmware after checksum verification
• Configuring WiFi, channels, and MAC filters

Configure a RuView sensing deployment, including WiFi settings, detection thresholds, processing on devices, and coordinated nodes. It covers device provisioning, server options, firmware variants, and Cognitum Seed integration to adjust how the system operates.

中文简介正在准备中。当前显示英语简介。

• Adjust WiFi channels and transmitter filters
• Tune presence, fall, and vital sensing settings
• Configure coordinated sensing across multiple nodes

Turn specifications and algorithm outlines into a system architecture. Define components, interfaces, data structures, and deployment plans, then document technology choices, security measures, failure handling, and plans for supporting increased usage.

中文简介正在准备中。当前显示英语简介。

• Turn specifications into a system design
• Define component responsibilities and API interfaces
• Plan for increased traffic and component failures

Build Claude applications using guidance for the official Anthropic SDK. Choose an integration approach, implement streaming and tool use, and follow workflows for model migration, prompt audits, evaluation, and cost optimization.

中文简介正在准备中。当前显示英语简介。

• Build a summarization app with Claude API
• Choose how to run an agent with custom tools
• Migrate existing code to a newer Claude model

Guide HyperFrames video projects from setup through layout checks, editable previews, and video output. Covers command-line workflows, environment troubleshooting, and distributed rendering on AWS Lambda, which splits video rendering work across cloud functions.

中文简介正在准备中。当前显示英语简介。

• Setting up a HyperFrames video project
• Checking text overflow and scene display
• Exporting a video after reviewing it in Studio

Guide HyperFrames video projects from setup and component selection through checks, previews, and rendering. Use command-line tools to inspect timelines, diagnose failures, compare frames, and choose local, batch, or cloud rendering for the finished composition.

中文简介正在准备中。当前显示英语简介。

• Set up and preview a HyperFrames video project
• Diagnose build or rendering failures
• Render multiple videos from variable data

Publish updated Chrome binaries to Remotion Lambda’s test region, update layer references and version documentation, and verify rendering with Docker before rolling the update out to all supported regions.

中文简介正在准备中。当前显示英语简介。

• Test a Chrome update before regional rollout
• Update Lambda layer references and Chrome version documentation
• Verify rendering with Docker across platforms

Guide test writing, updates, and reviews in Remotion by checking observable user outcomes. Choose integration, unit, visual, or end-to-end tests that detect broken workflows, and verify that bug fixes address the original regression.

中文简介正在准备中。当前显示英语简介。

• Choose a test boundary for a feature
• Review whether existing tests detect broken workflows
• Verify a regression test fails before the fix and passes after it

Create product demos, explainers, and social clips by choosing among AI footage, virtual presenters, code-based video templates, and editing tools. The skill guides scripts, visuals, captions, reusable production workflows, and exports suited to the target platform.

中文简介正在准备中。当前显示英语简介。

• Creating a product demo with screen recordings and captions
• Producing an explainer with an AI presenter
• Generating multiple social clips from one template

Plan game development workflows by matching engines, art and audio tools, automated playtests, packaging, publishing, and analytics to available tools and credentials. Compare options by cost, quality requirements, and offline availability.

中文简介正在准备中。当前显示英语简介。

• Plan a small Godot game for a game jam
• Combine AI-generated art with a simple game loop
• Choose tools for automated agent playtesting

Manage files and storage buckets in Tigris through its official CLI. Agents can upload and download objects, generate temporary sharing URLs, take snapshots, and manage access keys and permissions with structured JSON output.

中文简介正在准备中。当前显示英语简介。

• Upload, download, and copy files in Tigris
• Create temporary upload or download links
• Take a bucket snapshot before making changes