Spec2Cloud

Use when starting or refining a project's requirements, before any planning or coding. Supports sub-commands `sync`, `reverse`, and `validate`.

Use when local verification passed and the feature is ready to ship to Azure.

Use when a plan exists and the application source or IaC needs to be created or updated.

Use when a spec exists and an implementation or Azure deployment plan is needed, before writing code.

Use when the user wants to run the full Specify → Plan → Implement → Deploy loop end-to-end in one shot. Accepts a free-form prompt that is passed to specify.

Use when implementation exists and needs to be exercised locally against provisioned Azure dependencies, before deploying.

Create Azure architecture diagrams, flowcharts, data-flow visualizations, or illustrations as Excalidraw documents with embedded official Azure service icons, and export them as SVG and PNG. Use whenever the user wants to draw, sketch, diagram, visualize, or illustrate an Azure workload, solution, reference architecture, network topology, AI/ML topology, or any cloud system involving Azure services — even if they don't say "Excalidraw". Triggers include: "diagram", "architecture diagram", "draw", "sketch", "visualize", "flowchart", "data flow", "topology", "illustrate" combined with any Azure / cloud context. Also use to re-render existing `.excalidraw` files to SVG/PNG.

Execute pending tasks from tasks.md / tasks.json, updating both on completion.

Deploy the implemented feature to Azure once spec / plan / tasks / implement are complete.

Run the implemented feature on local servers (provisioning Azure-only dependencies first) to verify it works before deploying to Azure.

Package the Spec2Cloud spec-kit (preset + extension) as a single VS Code agent plugin under `plugins/speckit-spec2cloud/`. Use whenever the user wants to package, build, generate, refresh, or rebuild the spec-kit as an agent plugin, mentions "agent plugin", "VS Code plugin", "package the spec-kit", "publish skills as a plugin", or asks to mirror the preset/extension commands into the plugin layout described at https://code.visualstudio.com/docs/copilot/customization/agent-plugins.

Read-only consistency, coverage, and Azure-readiness analysis across constitution, spec, plan, and tasks.

Generate a domain-focused checklist that validates the quality of the requirements (completeness, clarity, consistency, measurability, coverage) — not the implementation.

Ask up to 5 targeted clarification questions to resolve ambiguity in the spec, then write the answers back into spec.md.

Create or update the project constitution (principles, non-negotiables, out-of-scope).

Create plan.md (technical context, architecture, design decisions) from the spec.

Create spec.md from a feature description.

Create tasks.md and tasks.json (dependency-ordered, phase-grouped) from plan and spec.

Publish Spec2Cloud spec-kit artifacts (extension, preset, workflow) together as a single GitHub Release. Use this skill whenever the user asks to publish, release, ship, or cut a release for the spec-kit — including phrases like "publish spec-kit", "publish the spec-kit", "release the spec-kit", or "cut a new spec-kit release". The skill bundles all three artifacts into one release whose version is the highest semver among the three manifests, and only publishes when that combined version is newer than the latest existing spec-kit release.

Select Microsoft Foundry models and regions, then configure azd environment variables (AZURE_LOCATION and AI_PROJECT_DEPLOYMENTS). Use when the user wants to choose, compare, or deploy AI models in Azure, set model deployments for azd provisioning, pick a region for AI workloads, or configure which models to deploy in their Azure AI Foundry project. Also use when user mentions model selection, model availability, region selection for AI, or azd env set for models.