A reference distilling the official documentation for AI/ML development features on Windows, centered on Windows AI Foundry. It covers built-in AI APIs, local ONNX inference (Windows ML), local model hosting (Foundry Local), agent integration (MCP / App Actions), low-level GPU inference (DirectML), and NPU hardware and profiling (Copilot+ PC / WPR / WPA). Depending on the user's task, read the appropriate README.md, and from there follow through to individual files.
Directory structure
skills/windows-ai/
SKILL.md
references/
ai-apis/
README.md
ai-dev-gallery.md
platform-card-click-to-do.md
platform-card-paint.md
platform-card-recall.md
platform-card-windows-studio-effects.md
faq-cloud-vs-local.md
choose-your-windows-ai-solution.md
content-moderation.md
copilot-plus-developer-guide.md
device-requirements.md
faq-using-ai.md
foundry-toolkit-vscode.md
phi-silica-structured-output.md
image-description-generator.md
image-foreground-extractor.md
image-generator.md
image-object-extractor.md
image-object-remover.md
image-scaler.md
language-model-best-practices.md
language-model.md
language-model-context.md
language-model-options.md
phi-silica-lora.md
platform-card-image-ai-apis.md
platform-card-phi-silica.md
platform-card-ocr.md
local-llms.md
recognized-text.md
responsible-ai.md
semantic-search.md
speech-recognition-model.md
text-intelligence-skills.md
text-recognizer.md
video-scaler.md
troubleshooting.md
windows-ml/
README.md
api-reference.md
bring-your-own-eps.md
check-ep-versions.md
deployment-bootstrap.md
eps-vs-bring-your-own.md
execution-provider-catalog.md
execution-provider-errors.md
execution-providers-overview.md
get-started.md
install-execution-providers.md
learning-model-binding.md
learning-model-evaluation-result.md
learning-model-session.md
learning-model.md
legacy-windows-machine-learning.md
logs.md
migrate-to-windows-ml.md
model-catalog-source-schema.md
model-catalog.md
model-compilation.md
model-conversion.md
models.md
onnx-runtime-inference.md
onnx-versions.md
overview.md
register-execution-providers.md
run-genai-onnx-models.md
samples.md
select-execution-providers.md
supported-execution-providers.md
tutorial.md
update-eps.md
webgpu-ep-experimental.md
winml-cli.md
foundry-local/
README.md
architecture.md
cache-management.md
installation-and-cli.md
model-catalog.md
overview.md
rest-api.md
sdk.md
winml-package.md
mcp-app-actions/
README.md
mcp-overview.md
mcp-server-overview.md
mcp-windows-identity.md
mcp-mcpb.md
mcp-manual.md
mcp-containment.md
test-mcp-server.md
quickstart-mcp-host.md
file-connector.md
odr-tool.md
app-actions-overview.md
actions-get-started.md
actions-uri-launch.md
actions-iactionprovider-manual.md
actions-filter-caller.md
actions-streaming-text.md
actions-remote-files.md
actions-availability.md
actions-display-ui.md
actions-json.md
actions-provider-manifest.md
actions-test-tool.md
actions-consume.md
actions-rai-safety.md
agent-launchers-overview.md
agents-get-started.md
agents-json.md
agent-workspace.md
security-consent-model.md
directml/
README.md
api-reference-constants.md
api-reference-enumerations.md
api-reference-functions.md
api-reference-interfaces.md
api-reference-structures.md
cuda-on-wsl2.md
debug-layer.md
dmlcreatedevice.md
directml-overview.md
directml-tools.md
directmlx.md
errors-and-device-removal.md
feature-level-history.md
fused-operators.md
gpu-accelerated-training.md
graphs.md
helper-functions.md
idmlbindingtable.md
idmlcommandrecorder.md
idmlcompiledoperator.md
idmloperator.md
idmloperatorinitializer.md
onnxruntime-directml.md
operators.md
programming-guide.md
pytorch-directml.md
resource-lifetime-sync.md
sample-applications.md
strides-padding-layout.md
tensors.md
tensorflow-directml.md
tensorflow-directml-faq.md
uav-barriers.md
version-history.md
webnn-overview.md
webnn-tutorial.md
npu-devices/
README.md
byom-model-sources.md
gpuview-npu.md
npu-hardware-overview.md
onnxruntime-etw-tracing.md
task-manager-npu.md
wpr-wpa-npu-profiling.md
Exploration procedure
Derive the category from the task, and identify the target page in the category's README.md:
- Find the category corresponding to the task in the mapping table below
- of that category
references/{category}/README.mdRefer to to identify the target page - Read the
.mdof the relevant page to check the details
Task → Category Mapping
| Task | Category | Reference README |
|---|---|---|
| I want to call on-device generative AI (Phi Silica) with LanguageModel | ai-apis | references/ai-apis/README.md |
| I want to implement image and OCR processing with TextRecognizer / ImageScaler / ImageObjectExtractor / ImageDescriptionGenerator | ai-apis | references/ai-apis/README.md |
| I want to apply SemanticSearch / ContentModeration / responsible AI guidelines | ai-apis | references/ai-apis/README.md |
| I want to select and prototype AI features using the Copilot+ PC development guide, AI Dev Gallery, and Foundry Toolkit | ai-apis | references/ai-apis/README.md |
| I want to run local inference of ONNX models with Windows ML | windows-ml | references/windows-ml/README.md |
| I want to select, register, install, and troubleshoot execution providers | windows-ml | references/windows-ml/README.md |
| I want to bind and evaluate models with LearningModel / LearningModelSession | windows-ml | references/windows-ml/README.md |
| I want to work with Windows ML's CLI, diagnostic logs, and WebGPU EP | windows-ml | references/windows-ml/README.md |
| I want to host an LLM locally with Foundry Local | foundry-local | references/foundry-local/README.md |
| I want to use Foundry Local's CLI / REST API / SDK / model catalog / cache management | foundry-local | references/foundry-local/README.md |
| I want to implement, register, and test an MCP server | mcp-app-actions | references/mcp-app-actions/README.md |
| I want to expose app functionality externally with App Actions / IActionProvider | mcp-app-actions | references/mcp-app-actions/README.md |
| I want to implement Agent Launchers / Agent Workspace / the security consent model | mcp-app-actions | references/mcp-app-actions/README.md |
| I want to directly control GPU inference devices, operators, and tensors with DirectML | directml | references/directml/README.md |
| I want to use the DirectML backend from ONNX Runtime / PyTorch / TensorFlow | directml | references/directml/README.md |
| I want to call GPU/NPU inference from a browser or app with WebNN | directml | references/directml/README.md |
| I want to check Copilot+ PC / NPU hardware requirements | npu-devices | references/npu-devices/README.md |
| I want to measure NPU utilization and inference with Task Manager / WPR / WPA / GPUView / ETW | npu-devices | references/npu-devices/README.md |
| I want to procure and quantize my own ONNX model for NPU (BYOM) | npu-devices | references/npu-devices/README.md |
This skill covers only AI/ML features under Windows AI Foundry (built-in AI APIs, local inference, agent integration, DirectML, NPU hardware and profiling). UI implementation such as WinUI controls, layout, and data binding is handled by windows-winui-controls, windows-winui-ui, and windows-app-sdk; packaging and distribution are handled by windows-packaging-publish; graphics and media rendering are handled by windows-graphics-media.