delano

Define and approve a measurable outcome and Spec. Use when a new delivery request has unclear scope, missing outcome, or missing owner.

Execute mapped tasks with stream discipline, dependency safety checks, and evidence updates. Use when tasks are ready for implementation.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

Decompose an approved plan into atomic tasks with dependencies and acceptance criteria. Use when planning is complete and execution must be prepared.

Verify release readiness and enforce quality gates with risk-based checks and evidence capture. Use before closure or merge.

Open and run repo-native research intake before mutating canonical delivery artifacts. Use when a Delano request has unclear intent, unresolved options, external evidence needs, or material uncertainty that should be investigated before changing spec, plan, workstreams, or tasks.

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Run a time-boxed Prototype Probe to retire material uncertainty before spec approval. Use when `spec.md` is still draft, `probe_required` is true, or a narrow experiment is needed to bound technical or delivery risk before planning.

Close the delivery loop and capture completion evidence, status updates, and handoff artifacts. Use after quality gates pass.

Analyze a repository `AGENTS.md` before broader work begins and improve it only when the user gives explicit approval. Use when the user wants a first-pass review of repo instructions, wants to tighten `AGENTS.md` quality, or needs a compact operating-rules and source-of-truth map for future agent turns.

Repair and maintain `.project/context/` so it reflects current project reality. Use when context files are stale, contradictory, still template-like, after major scope or architecture changes, before handoff, or when execution friction suggests context debt.

Distill reusable decisions and lessons into project memory and improvement actions. Use at milestones, closeout, or recurring failure patterns.

Translate an approved Spec into an executable Delivery Plan and workstreams. Use after spec approval before task decomposition.

Reconcile local contracts with Linear and GitHub state, repair mapping and status drift, and update registry files. Use when task state changes or sync drift is suspected.