laguagu/claude-code-nextjs-skills / skills/ai-app
ai-app
VerifiedBuilds full-stack Next.js AI applications with the AI SDK and the shadcn/ui AI Elements patterns. Use when creating a chatbot, agent dashboard or custom AI application.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.5 KB |
| references/agent-dashboard.md | markdown | 1.2 KB |
| references/chatbot.md | markdown | 1.2 KB |
| references/examples.md | markdown | 771 B |
| references/project-structure.md | markdown | 896 B |
references/agent-dashboard.md
View on GitHub# Agent dashboard contract
Use `ai-sdk` to select the installed-major agent API and the shadcn/ui AI
Elements patterns (Trace, Tool, Plan, Queue; https://ui.shadcn.com/docs/ai-elements)
for execution UI, or `ai-elements` for components already installed. A
dashboard should expose the run's purpose, current state, useful results and
actions the user can take.
Keep server execution state separate from transient display state. Stable run
and tool-call IDs connect streamed updates, stored results and approval decisions.
Handle cancellation, timeout, tool failure and process restart according to the
chosen runtime; an in-memory loop does not provide durable resumption.
Approvals must pause the operation before its side effect and bind the decision
to the actual server-issued request. Denial is a terminal tool outcome, not a
loading state. In AI SDK 6 use tool-level `needsApproval`; for SDK 7 follow the
selected agent's approval API, including WorkflowAgent's separate semantics.
Multiple agents, model selectors, timelines and metrics are optional. Add them
only when they help the user operate the app. Verify approval/denial and tool
transitions in the browser, not just successful model output.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |