exa-webfetch
Uses Exa API for intelligent web searches instead of default WebFetch. Provides up-to-date information with semantic search capabilities.
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Uses Exa API for intelligent web searches instead of default WebFetch. Provides up-to-date information with semantic search capabilities.
Deep learning with PyTorch - model training, GPU acceleration, and data science workflows
ByteHouse AI Query Skill, providing Text2SQL interface capabilities, supports converting natural language into SQL and executing queries. This skill is used when users need to convert natural language…
使用本地 MinerU 解析文档。当用户输入或附带 PDF、DOCX、PPTX、XLSX、TIFF/TIF 或批量图片(jpg/jpeg/png/bmp/tif/tiff)文件时,默认调用 MinerU 将其解析为 Markdown 再读取;单张 jpg/jpeg/png/bmp 图片直接用 Read 工具读取;其他格式使用 Opencode 默认解析。触发词:mineru、pdf、docx、pp…
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, dev…
Search and monitor arXiv papers. Query by topic, author, or category. Track new papers, download PDFs, and summarize abstracts for research workflows.
Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generation. Use this skill when: (1) Designing binder scaffolds for a target protein, (2)…
Analyze images, screenshots, diagrams, and visual content - Use when you need to understand visual content like screenshots, architecture diagrams, UI mockups, or error screenshots.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search,…
AI video generation prompting guide for Sora 2 and Higgsfield.ai
用于下载 Bilibili 用户个人的收藏夹视频,支持批量下载、大小过滤、最高清晰度等功能。
图片或者视频提示词生成的skill
检测仔 — AI原创检测绕过处理器方案。🏆(H+方案)实测SubmitHub光谱Human 78%/时域Human 91% Human made 🎉。
Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels.
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants t…
Generate pedagogically-aligned slide decks from educational content using NotebookLM. Use when creating chapter slide presentations with proficiency-calibrated prompts. NOT for static slides or non-ed…
Music production expert for recording, mixing, mastering, and DAW workflows
AI-powered task management for structured, specification-driven development. Use this skill when you need to manage complex projects with PRDs, break down tasks into subtasks, track dependencies, and …
录音逐字稿清洗:读取沟通录音目录下带 -待清洗 后缀的逐字稿,脚本机械清洗 + AI 语义清洗两层接力,说话人识别、术语纠错、7 道闸门验证,全程不打断用户(三级裁决 + 批次报告,沉默即通过)。当用户说"清洗""洗稿""处理逐字稿""清洗这份录音"时使用。
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation,…
Extracts key terms from contracts, identifies risks, flags unusual provisions
Legal demands two things: frontier-level reasoning and precision document generation. CellCog delivers both. #1 on DeepResearch Bench (Feb 2026) for the intelligence that legal work requires, paired w…
Comprehensive skill for Microsoft GraphRAG - modular graph-based RAG system for reasoning over private datasets
Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task li…