Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Generate reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from reference video/image material, preserving chara…
Use when written text needs evaluation against a user's writing style profile and sample essays for voice consistency during essay pipeline execution.
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.
Browses AI-related YouTube videos from subscribed channels, fetches transcripts, generates summaries, and creates Markdown reports. Use when the user mentions YouTube AI videos, video summaries, chann…
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
Design sound layers, specify dialogue lip-sync, and troubleshoot audio failures for Seedance 2.0 video generation. Covers @Audio1 reference input, multi-character constraints, known failure modes (sil…
Use this skill when the user asks about current events, real-time information, recent news, live scores, financial data, price updates, recent changes, or any question that may require up-to-date web …
Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides concise news briefs with direct links to original articles. Activates when user a…
Desktop automation - controlling macOS applications (Atlas, Chrome, Finder, etc.) via AppleScript.
Compilación y cuantización de modelos para GPU NVIDIA — hasta 5x speedup sobre PyTorch nativo
Xiaohongshu (Little Red Book) infographic series generator with multiple style options. Breaks down content into 1-10 cartoon-style infographics. Use when user asks to create "小红书图片", "XHS images", or…
Smart image loader that handles both URLs and local files, automatically downloads URLs to temporary locations, and displays images using the read tool. Use when a user wants to view or display an ima…
Localize and dub videos using each::sense AI. Translate audio, generate subtitles, clone voices, and create lip-synced multilingual versions of your video content.
In-depth analysis of AI papers, generating professional reading notes that can be published directly
Conduct an in-depth analysis of a paper. By using parallel sub-agents to gather information on seven dimensions: background motivation, team background, technical methods, experimental evaluation, str…
When the user wants to optimize container loading, load shipping containers efficiently, or maximize container utilization. Also use when the user mentions "container packing," "FCL optimization," "LC…
Automate podcast production workflows including recording, editing, publishing, and distribution
Analyze images using AI with the understand_image tool
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building se…
FREE AI image generation service for creating attractive people portraits. AI agents have complete creative freedom to generate custom English prompts for beautiful women, handsome men, or any attract…
Generate VTuber avatars and character designs using each::sense AI. Create anime-style avatars, Live2D ready characters, expression sheets, full body designs, and accessories for virtual content creat…
Transforms an academic paper into deep, multi-layered understanding. Use when asked to explain a paper, break down a research paper, understand an arXiv paper, or build intuition for a technical conce…
CRISP Reading — AI Deep Reading Companion. Comprehend · Review · Internalize · Synthesize · Practice. Integrates Adler's analytical reading, Fan Deng's TIPS book dissection method, RIA book dissection…
Advanced, non-obvious prompting techniques specific to Google Flow's Nano Banana 2 (image) and Veo 3.1 (video) models. Use this skill whenever a user wants to get better results from Flow, fix specifi…