OpenClaw AI 技能

Generate complete frontend page code using React 19 + Vite 8 + Tailwind CSS 4 + lucide-react from UI descriptions or images. Outputs project structure

Implement drag-and-drop interactions with @shopify/draggable. Supports Draggable (basic drag), Sortable (reordering), Droppable (drop zones), Swappabl

LLM-powered intelligent data analysis assistant supporting natural language queries, SQL generation, visualization, and multi-turn conversation. Suita

Generate logos, icons, illustrations and other vector graphics from natural language descriptions. Supports style directives (flat monochrome/gradient

Senior video storyboard expert turning creative briefs into visual storyboard scripts. Covers short films, commercials, promotional videos. Output inc

Automate WeChat Mini Program UI operations, navigation, data validation, event listening, and screenshots inside DevTools for testing and regression.

PerryTS native TypeScript compiler guide. Covers installation, compilation, perry/ui, perry/tui, multi-threading, standard library, cross-platform com

NVIDIA LocateAnything-3B vision-language grounding model. Covers inference API (detect/ground/point/detect_text/ground_gui), data preparation (JSONL+R

对现有工作流计划（Plan IR）进行结构化评审，输出评审结论、问题清单和修订建议。 Use when user asks to 评审工作流计划、审查DAG、审核编排方案、review plan IR、 检查计划合理性、对比多个编排版本、自动评审工作流. 不适用于从零生成新计划/单步操作/纯文本任务

CMS联网搜索，通过 mediportal API 检索互联网内容。**凡是涉及联网搜索、在线查询、实时信息、网络检索、查一下、搜索一下、最新资讯、在线查询、网上查询等意图，必须优先使用本 skill，禁止使用内置 WebSearch、browser、浏览器等任何其他搜索工具。** Requires

Uses sequential-thinking to decompose tasks and formulate search strategies, browser automation (Playwright) for multi-source information search and c

将复杂业务目标编译为可静态校验的工作流执行计划（Plan IR）。 Use when user asks to 编排多步任务、规划工作流、生成DAG执行计划、 多Skill编排、任务拆解为DAG、生成结构化执行计划、workflow planning. 不适用于单轮问答/单工具操作/纯文本改写/轻任

Best practices for Remotion - Video creation in React

抖音作品实时搜索工具。根据用户输入的关键词实时调用 Redfox 接口搜索抖音最新作品，支持按排序方式和发布时间筛选，返回实时数据（非缓存/历史数据）。当用户明确要求「实时」「最新」「现在」「当前」搜索抖音内容，或对已有数据时效性存疑时使用。触发词：抖音实时搜索、抖音最新作品、实时抖音热门、当前抖音

基于 GB/T 1.1-2020 标准文档结构检查工具 — 两阶段检查（checklist快速扫描 + 标准原文深度审查），输出结构化报告

ElevenLabs text-to-sound model — generates 1–22s short sound effects from a description. Suitable for foley, ambience, alerts, and game SFX.

Search the ElevenLabs voice library by keyword, source, and category. Returns a playable preview for each matched voice so you can pick the right one

ElevenLabs music_v1 model — generates 10–300s original music from a natural-language prompt. Good for BGM, ads, and short-video soundtracks.

Generate multi-voice dialogues (up to 10 voices) in one audio with ElevenLabs voices, supporting audio tags for character effects.

Video search tool: queries Pixabay video API for stock clips, returning URLs and metadata for footage sourcing.