开发技能

Review a completed implementation task against approved requirements, design, and assigned scope. The skill inspects code changes and verification evidence, checks tests and hidden dependencies, and returns an approval or rejection with specific findings and required fixes.

中文简介正在准备中。当前显示英语简介。

• Reviewing a task after implementation
• Rechecking fixes after a rejected review
• Checking for changes outside the approved task scope

Create topic-specific project guidance that agents can use as project memory. Examine existing code and available templates to document conventions for areas such as APIs, testing, authentication, or deployment, with concrete examples.

中文简介正在准备中。当前显示英语简介。

• Documenting project-specific API conventions
• Recording test organization and mocking practices
• Sharing authentication and permission patterns

Implement approved tasks through test-driven development, writing tests before code. Run all pending tasks sequentially with subagents or select tasks for direct execution, then track completion using reviews and verification evidence.

中文简介正在准备中。当前显示英语简介。

• Running all pending approved implementation tasks
• Implementing selected tasks by number
• Developing features with tests written first

Generate requirements, technical designs, and implementation tasks for pending roadmap features in Cascade. Features are processed one at a time in dependency order, followed by a review of consistency and responsibility boundaries across specifications.

中文简介正在准备中。当前显示英语简介。

• Generate specifications for multiple features in Cascade
• Process feature specifications in dependency order
• Check shared data and interfaces across specifications

Add coding-agent support to cc-sdd through a documented workflow. Research the agent’s official formats, prepare an integration plan, implement registry entries and templates, and verify generated files, including Japanese and English output.

中文简介正在准备中。当前显示英语简介。

• Adding support for a new coding agent
• Adding an agent variant with subagent support
• Planning migration to SKILL.md-based templates

Compare feature requirements with existing code to identify missing capabilities and integration challenges. Evaluate extending current components, building new ones, or combining both, and save the findings to guide technical design.

中文简介正在准备中。当前显示英语简介。

• Planning a new feature in an existing system
• Comparing component reuse with new development
• Identifying integration questions before design

Review specification files to see the current phase, completion levels, and remaining tasks. Get a progress report that identifies next steps, blockers, dependencies, and related specifications that may need checking after changes.

中文简介正在准备中。当前显示英语简介。

• Check a specification’s progress and remaining tasks
• Identify next steps and blockers
• Review related work that may need checking after changes

Turn a project description and existing project guidance into a requirements document. Organize expected behavior into EARS statements, a structured format for clear conditions and outcomes, and review coverage, ambiguity, and scope before saving.

中文简介正在准备中。当前显示英语简介。

• Turning a feature idea into testable requirements
• Clarifying what a feature includes and excludes
• Aligning requirements with existing project guidance

Build an adapter that exposes API, database, or object storage data as files in Mirage. Covers Python or TypeScript implementation, mount configuration, and tests for reading, access restrictions, and supported changes.

中文简介正在准备中。当前显示英语简介。

• Connect an API or database to Mirage
• Implement file operations for a custom data source
• Package a reusable Mirage adapter

Develop reusable external Holoscan Modules with the Holoscan CLI, from scaffolding and testing to Python bindings and package creation. Verify that applications can use installed packages in a clean environment, with checks for each requested format.

中文简介正在准备中。当前显示英语简介。

• Creating a reusable Holoscan operator module
• Adding and testing Python bindings
• Using an installed module from another application

Diagnose a specific failing, hanging, or incorrect Holoscan CLI command. The skill guides reproducible investigation, isolates the responsible layer, applies a minimal fix, and checks the same command and focused tests to verify the result.

中文简介正在准备中。当前显示英语简介。

• Diagnose a reproducible holoscan build failure
• Investigate a command that hangs
• Trace unexpected application output

Choose the appropriate NVSHMEM performance workflow for collecting benchmark evidence, selecting communication between nodes, assigning network adapters to processing elements, or assessing TMA transfers between peer GPUs. This skill routes requests to specialists that perform the technical work.

中文简介正在准备中。当前显示英语简介。

• Choose a workflow for baseline performance measurement
• Find the specialist for inter-node transport selection
• Route network adapter assignment questions

Find official NVSHMEM and NVSHMEM4Py documentation for installation, APIs, runtime settings, and troubleshooting. Receive concise explanations with direct source links, relevant version details, and explicit uncertainty when the requested documentation or compatibility evidence cannot be verified.

中文简介正在准备中。当前显示英语简介。

• Finding installation instructions for a specific release
• Understanding APIs and runtime settings
• Checking NVSHMEM4Py compatibility

Review or prepare an NVSHMEM CUDA kernel for TMA, a GPU data-transfer mechanism. Assess hardware suitability, add shared-memory registration and launch settings, and consider direct transfers from shared memory when an intermediate copy is proven redundant.

中文简介正在准备中。当前显示英语简介。

• Assessing TMA suitability for an NVSHMEM kernel
• Preparing a selected kernel and its launch settings for TMA
• Reviewing whether an intermediate memory copy can be removed

Diagnose NVSHMEM launch failures, crashes, hangs, and communication problems using exact commands and complete logs. Separates observations from likely causes, checks version-specific documentation, and prepares a Markdown bug report for the user to submit.

中文简介正在准备中。当前显示英语简介。

• Investigate launch failures, crashes, and hangs
• Distinguish NVSHMEM defects from application or environment issues
• Check whether a known issue applies to the installed version

Assess whether NVSHMEM suits communication between GPUs, then learn its core concepts and plan a first C/C++ or Python program. Guidance covers program structure, compilation, launch commands, and appropriate next steps.

中文简介正在准备中。当前显示英语简介。

• Assessing whether NVSHMEM fits a multi-GPU application
• Learning GPU communication and shared-memory concepts
• Designing, compiling, and launching a first C/C++ program

Connect Omniverse scenes to the Newton physics engine through ovnewton. The skill guides scene import, simulation stepping, synchronization of scene edits, and publication of simulation results for rendering, with setup guidance for supported solvers.

中文简介正在准备中。当前显示英语简介。

• Importing a populated ovstage into Newton
• Applying scene edits to a running simulation
• Publishing physics results for Omniverse rendering

Guide the creation and maintenance of an agent’s ethos.md, a record of its purpose, boundaries, and success criteria. Locate existing files and route requests to intent exploration or editing, carrying forward information already confirmed.

中文简介正在准备中。当前显示英语简介。

• Defining a new agent’s purpose and boundaries
• Locating an existing ethos.md and identifying gaps
• Updating specific rules or revisiting the agent’s intent

Diagnose slow loading, high memory use, and low frame rates in USD 3D scenes. It coordinates measurement, scene validation, and optimization, then produces reports comparing available before-and-after evidence and an optimized scene when changes are performed.

中文简介正在准备中。当前显示英语简介。

• Investigate slow loading in USD scenes
• Diagnose low frame rates and high memory use
• Review repeated structures in large CAD scenes

Generates a standalone YOLO26 detection and tracking service scaffold for VSS Search and Alerts. Includes DeepStream configuration, Docker files, and tests, with Kafka integration guidance and clear limits on validation before model assets are available.

中文简介正在准备中。当前显示英语简介。

• Creating a standalone YOLO26 service for VSS
• Generating a scaffold before model assets are ready
• Checking Kafka integration with VSS workflows

Build apps for viewing USD, a 3D scene format, using guidance matched to browser streaming or local execution. The skill selects implementation references for rendering, camera controls, selection, interface layout, and validation.

中文简介正在准备中。当前显示英语简介。

• Build a browser viewer for USD scenes
• Create a local workstation viewer
• Add camera controls and object selection

Integrate NVIDIA NeMo Fabric into an application or evaluation system through its Python SDK. Map application settings into typed configuration, choose an execution lifecycle, validate prerequisites, and handle standardized results, artifacts, and telemetry.

中文简介正在准备中。当前显示英语简介。

• Integrate agent execution into an application
• Build configurations for different evaluation conditions
• Manage single calls and conversations with retained state

Wrap existing tool functions and language model calls with NeMo Relay to record execution events, process requests through middleware, and apply guardrails. Guides integration while preserving the original functions’ arguments, results, and business logic.

中文简介正在准备中。当前显示英语简介。

• Adding execution events to existing tool calls
• Wrapping model provider calls with NeMo Relay
• Integrating request processing and execution guardrails

Build, migrate, and review adapters that connect external agent runtimes to NVIDIA NeMo Fabric. It guides configuration translation, startup and shutdown, discovery metadata, and validation against the public contract, the rules defining how adapters interact with Fabric.

中文简介正在准备中。当前显示英语简介。

• Building an adapter for an external agent runtime
• Migrating an adapter to the public contract
• Reviewing configuration mapping and runtime isolation