Dernières compétences

Query and process Shopee returns, refunds, and disputes across all 15 Returns module APIs.

Query Shopee store escrow, payout, wallet, and income-report data via 18 Payment module APIs.

Answer TCM diagnosis and classical-formula questions in the style of 倪海厦, grounded in 伤寒论 and 金匮.

Skill 标准化规范引擎。支持 R-01~R-26 规范审查（audit / create / update / refactor / bump / readonly 六模式），含权限扫描、数据目录合规检查、渐进式加载、LLM 二次筛分类。

全平台统一发布工具。支持 skills 和 agents 的 Gitee/GitHub/ClawHub/SkillHub/PyPI 同步与 Release 创建，LLM 驱动的文件过滤与脱敏。

Draft, rewrite, or review Chinese official documents and formal working materials with strict fact boundaries.

Maintain a dynamic A-share pool (≤30 names) with quantitative scoring, technical timing, and scheduled push alerts.

Read and manage Google Calendar events through authenticated REST API calls.

Live front-page headlines from 20 countries with searchable archives for breaking news and comparative analysis.

Track global hot events and trace their impact to A-shares, HK/US stocks, sectors, and commodities with scheduled push.

Generate short video spoken scripts using a fixed 7-step structure with hooks, stories, and a punchline ending.

Turn creative briefs into industry-standard storyboards through a gated four-state workflow with per-step user confirmation.

Get platform-tuned social-media post designs and copy that match each platform's native specs, safe areas, and engagement style.

A two-phase workflow for designing social-media carousels, from intent confirmation to cover-first generation.

End-to-end marketing brochure design with a layout-first workflow and mandatory approval before delivery.

Generate Amazon-compliant main, secondary, and A+ images through a stepwise, confirmation-driven workflow.

Tongyi Wanxiang 2.7 video model 鈥?one model covers text-to-video, first/last-frame-to-video, and reference-to-video.

Generate high-quality images with Vidu Q2. Supports text-to-image and image-to-image. 使用 Vidu Q2 生成高质量图像，支持丰富的文生图与图生图指令。

Convert static images into dynamic videos using Vidu Q2 image-to-video model. 使用 Vidu Q2 图生视频模型，将静态图片通过智能运镜转化为动态视频。

Clone voice and generate new text reading audio with one click using Vidu Audio Clone. 使用 Vidu 声音克隆技术，通过参考音频一键复制音色并生成新文本的朗读音频。

Generate videos from prompts, images, or frames with automatic model selection.

Fast response and generation of short videos with Google Veo 3.1 Fast. 使用 Google Veo 3.1 Fast 极速版模型，快速响应并生成短时长的文生视频或图生视频。

Generate high-quality cinematic effects videos with Google Veo 3.1. 使用 Google Veo 3.1 模型，生成高质量的电影级特效视频，支持文生视频与图生视频。

Upscale images via a cloud super-resolution API and get back a hosted enhanced image URL.

Generate vocal or instrumental music via Suno with auto-lyrics or custom lyrics modes.

Fast image generation with Doubao Seedream 5.0 Lite. Supports text-to-image and image-to-image. 使用豆包 Seedream 5.0 Lite 极速生成图像，支持文生图与图生图。

Generate high-quality images with Doubao Seedream 4.5. Supports text-to-image and image-to-image. 使用豆包 Seedream 4.5 模型生成高质量图像，支持文生图与图生图。

Run ByteDance's Seedance 2.0 Fast video model from the dLazy CLI, using text prompts, reference media, or first/last frames.

Generate videos from prompts, images, videos, audio, or first/last frames via a CLI for Seedance 2.0.

Generate videos with the PixVerse C1 model from the dLazy CLI.

Generate Midjourney-style images from a prompt with control over aspect ratio, bot type, and grid or single-image output.

Generate videos from text prompts and reference images using the Kling v3 Omni model via the dLazy CLI.

Powerful video generation with Kling v3. Supports high-quality text-to-video and image-to-video. 使用可灵 (Kling) v3 强大的视频生成模型，支持高质量的文生视频与图生视频。

Generate exquisite images with Kling o1 model. Supports text-to-image and image-to-image. 使用可灵 (Kling) o1 模型生成精美图像，支持文生图与参考图生图。

Generate customized speech that highly restores the timbre by uploading reference audio using Kling Audio Clone. 使用可灵 (Kling) 声音克隆模型，通过上传参考音频，生成高度还原该音色的定制语音。

Convert text into high-quality, emotional speech reading using Kling TTS. 使用可灵 (Kling) TTS 模型，将文本转化为高质量、情感丰富的语音朗读。