laguagu/claude-code-nextjs-skills / skills/nextjs-chatbot
nextjs-chatbot
VerifiedProduction Next.js web-chat integration: tool approval, persisted conversations, tool result UI, grounded retrieval, follow-up suggestions and embedded widgets. Use when building or debugging a web chatbot that needs these features. Use nextjs-shadcn for scaffolding and ai-sdk for general SDK APIs; multi-platform bots use Chat SDK.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.6 KB |
| hitl.md | markdown | 4.1 KB |
| persistence.md | markdown | 4.0 KB |
| popup-widget.md | markdown | 1.6 KB |
| search.md | markdown | 1.8 KB |
| suggestions.md | markdown | 1.4 KB |
| testing.md | markdown | 2.2 KB |
| tool-rendering.md | markdown | 1.7 KB |
| web-search.md | markdown | 1.6 KB |
suggestions.md
View on GitHub# Follow-up suggestions
Add suggestions when they help the user take a plausible next step. They are
optional; an answer does not need a fresh chip row every time. Existing tool
choices or unanswered options often work better than an extra model call.
When the assistant asks for a choice or confirmation, suggest valid replies to
that request. Offer new follow-up questions after a completed answer.
Ground suggestions in the available answer, source records and supported
actions. Preserve names and options accurately, and do not invent categories
or promise unavailable data. A suggested question and a button that executes
a side effect need distinct behavior; execution still requires authorization
and any required approval.
If a model generates suggestions, use a small validated output schema and
choose a supported model from measured quality/cost/latency. Tie the request
to the conversation and answer IDs, cancel or discard stale results after a
new turn, and allow generation failure to leave no suggestions.
Keep labels readable at the actual viewport and language. Wrap or lay them out
without clipping; fixed word counts and mandatory single-line chips do not
generalize. Suggestions should complement the answer instead of duplicating
it or displacing the composer.
Verify unavailable entities, incomplete answers, conversation switching,
screen-reader names and narrow layouts.
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 |