Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Expert ComfyUI workflow builder for consistent AI character generation across image, video, and voice. Triggers on requests to create ComfyUI workflows, generate character-consistent images/videos, tr…
Generate and direct cinematic AI videos with Seedance 2.0 (ByteDance/Dreamina/Jimeng). Covers text-to-video, image-to-video, video-to-video, and reference-to-video workflows with @Tag asset references…
Stock technical analysis expert - providing professional K-line patterns and technical indicators analysis, offering investment advice
Extract subtitles from Bilibili videos, transcribe videos without subtitles, and generate structured summaries. Trigger conditions: Bilibili URL (bilibili.com), BV ID (BV1xxx), or requests like "extra…
For creators making surreal short videos that blend rough glowing hand-drawn animation with live-action spaces. Users provide a scene idea, contact object or hand, desired mood, and optional language …
Qwen3-TTS text-to-speech skill, supporting multilingual speech synthesis, voice cloning, and voice design. This skill is used when users need to generate speech, convert text to speech, or utilize TTS…
Fake news/rumor verification: Used when a user asks 'Is this true?', 'Help verify the truth', 'Debunk', or provides a piece of text/link to check its authenticity. Fact-check the credibility of inform…
An LLM-driven daily stock analysis system. It supports intelligent analysis of selected stocks from A-shares, HK stocks, and US stocks, generating decision dashboards and market review reports. Provid…
抖音全网实时热点适合内容创作者、运营、电商、营销在用户想知道现在最热门的抖音热点时使用，帮助基于输入材料生成实时热点、当前热榜内容、值得即时跟进的话题。
Download Douyin videos to local (preferably without watermark). Used for providing original material for subsequent video analysis/reproduction, supports input of URL or video_id, batch list input, an…
Huawei Ascend NPU model compression tool (msModelSlim). Use for LLM quantization (W4A8, W8A8, W8A8S, W8A16), MoE model compression, multimodal model compression (Qwen-VL, InternVL, HunyuanVideo, FLUX,…
Alibaba Cloud Media Processing Service (MPS) one-stop video processing skill. Use when users need video processing, transcoding, snapshot generation, content moderation, or video upload. For video dis…
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
For creators explaining science, education, or general knowledge through tactile handmade papercraft visuals. Users provide a topic, core knowledge points, or source material and may specify audience,…
An AI-assisted video editing workflow for cutting, building, and enhancing live-action footage. It covers the entire process from raw shooting to FFmpeg, Remotion, ElevenLabs, fal.ai, and then final t…
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频",…
For musicians, video creators, and social-media editors producing AI music videos or emotional short films with lyric typography. Users provide music, lyrics, references, characters, typography direct…
For marketers and creators producing promotional content for brands, products, websites, apps, shops, or personal projects. Users provide logos, product images, interface screenshots, official links, …
抖音最具商业价值意见领袖（KOL）适合内容创作者、运营、营销、品牌方在用户想找值得合作的抖音达人时使用，帮助基于输入材料生成相关创作者 / KOL、对标账号候选、合作和竞品研究线索。
Turn product images and ad requirements into minimalist product ad shorts for e-commerce promotion and product launches. The Skill confirms format and product variants, extracts selling points, writes…
帮自媒体人把文章内容自动转化为精美的系列信息图（小红书图文/公众号配图）。
Automatically generate illustrations for articles, supporting AI-generated images, public domain images, and free stock photos, and upload them to the ImgBB image hosting service to create Markdown li…
For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge points, opinions, or abstract topics. Users provide source copy, story beats, or a …
For users creating a two-player co-op game menu or opening animation. Users provide two player names, a game title, a target visual style, and optional character reference images. The Skill locks iden…