Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Guides users through AI video production on the Seedance (即梦) platform — from creative ideation and asset preparation through storyboarding to production-ready prompts. Activates on keywords like Seed…
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and…
Agente that simulates Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo. Use quando quiser: aprender deep...
This skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph", "track entities", or mentions memory architecture, temporal knowledg…
帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“产品图生成”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 产品图生成, text-to-i…
Paper Review (Step 2 of a 3-step pipeline). Read the enriched paper data, scan the note library, generate opinionated review recommendations, save the recommended files to Obsidian, update history; gi…
Scientific research and analysis skills
Analyze construction drawings to extract dimensions, annotations, symbols, and metadata. Support quantity takeoff and design review automation.
Create diagrams, charts, and visual assets for security documentation. Generate network diagrams, architecture visuals, and data visualizations. Use when creating visual content for reports or present…
Comic style video generator - specifically designed to create animated videos in comic styles such as Japanese healing, Chinese ink wash, and American cartoons. It comes with 8 built-in comic style te…
Generate videos based on text descriptions, a workflow skill for generating images and videos. Dependent skills: byted-web-search, image-generate, video-generate. Note: This workflow does not have an …
Conducts a guided conversational interview with the user about the image or scene they want to create, asking pertinent questions to fully understand their vision, then synthesizes a perfect model-app…
Creative writing and storytelling powered by CellCog. Create stories, novels, screenplays, fan fiction, world building, character development, narrative design. AI-powered creative writing assistant.
Generate character voices using TTS, voice cloning, and lip-sync tools. Supports Chatterbox, F5-TTS, TTS Audio Suite, RVC, and ElevenLabs. Use when creating speech audio for characters or syncing audi…
Analyze financial reports of listed companies (US/Japan/HK/A-shares), and generate valuation analysis and investment reports
Summarizes articles or text, presenting key information in a concise format. Adapts to prioritize completeness over brevity when requested, ensuring no critical details are lost.
基于 LLM 的微信公众号股票情报自动提取与结构化平台 微信公众号是 A 股散户和游资获取题材炒作、行业分析、公司调研信息的核心渠道，但文章内容非结构化、信息密度高、且涉及多只股票相互关联。人工阅读 → 摘录 → 录入数据库，耗时且容易遗漏关键数据点。本项目旨在通过 LLM + 自动化流水线 将这一流程缩短到 1 分钟。
B站短视频运营增长助手适合内容创作者、运营、品牌方、电商在用户提供了 B 站视频链接时使用，帮助基于输入材料生成评论情绪和讨论结构、观众画像和兴趣信号、内容与互动建议。
Compress and simplify prompts to preserve meaning while reducing use
将剧本、场景或广告创意说明拆成可执行的分镜表，并制作一至四张关键分镜图。
Use this skill to generate AI images using ModelScope's Tongyi-MAI/Z-Image-Turbo model. Simply describe the image you want and it will be generated. Supports Chinese and English prompts.
Generate professional slide deck images from content. Creates comprehensive outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a pre…
Generate mind map images using mind-elixir. Produces PNG or SVG files from plaintext input. Use when the user needs a mind map, concept map, or topic overview diagram.
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and introduces randomized "mutations" to break local optima.