Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Patterns for running AI models locally in browsers using WebGPU, Transformers.js, WebLLM, and ONNX Runtime. Zero API costs, full privacy. Use when 'on-device AI, browser AI, WebLLM, Transformers.js, W…
Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunoflu…
Source royalty-free images and videos from Pexels API for design, placeholders, or content. Supports search, curated/popular content, collections, multiple resolutions, and ALWAYS creates detailed sid…
Guide users through OmicVerse plotting utilities showcased in the bulk, color system, and single-cell visualization tutorials, including venn/volcano charts, palette selection, and advanced embedding …
Converts run telemetry and user notes into structured reflections with confidence scores. Use after runs to capture qualitative feedback and generate next-step guidance with safety checks for pain or …
Autonomous prior art search and analysis agent. Searches multiple databases, analyzes references, creates claim charts, and assesses patentability impact.
AI video pipeline validator for Veo 3 feasibility, 8-second scene chunking, and shot continuity. USE WHEN: Validating screenplays for AI video generation, chunking scenes into 8-second segments, gener…
Model quantization for efficient inference and training. Covers precision types (FP32, FP16, BF16, INT8, INT4), BitsAndBytes configuration, memory estimation, and performance tradeoffs.
Build agentic AI with OpenAI Responses API - stateful conversations with preserved reasoning, built-in tools (Code Interpreter, File Search, Web Search), and MCP integration. Prevents 11 documented er…
Parallel PDF to MP3 conversion using MiniMax. Convert multiple PDF chapters to audio simultaneously using parallel subagents. Use when: (1) User says 'generate mp3 for the story of [STORY_NAME]', (2) …
Kickstart and maintain a fast-paced fiction project from a thumbnail using Harmon Story Circle + Crouch-style chapter momentum. Use when the user asks for help writing a story/novel, wants beat sheets…
Based on the text provided by the user or the content of the user-specified txt/md file, select the appropriate text type from the list of types, and provide a podcast live script in the specified for…
Automatically activated before chapter writing, enforcing a 9-item must-read document checklist - to prevent AI focus degradation in long novels by ensuring all context is loaded before each writing s…
Process synced Granola meetings to update person pages, extract tasks, and organize meeting notes
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production p…
This skill should be used when users need comprehensive research on a topic requiring exploration of multiple sources, synthesis of findings, and a well-structured report with citations. Use for compl…
Implement research papers from arxiv. Use when the user provides an arxiv link, asks to implement a paper, or wants to reproduce research results.
Source royalty-free images and videos from Pexels API for design, placeholders, or content. Supports search, curated/popular content, collections, multiple resolutions, and ALWAYS creates detailed sid…
Real-time rope/cable physics using Position-Based Dynamics (PBD), Verlet integration, and constraint solvers. Expert in quaternion math, Gauss-Seidel/Jacobi solvers, and tangling detection. Activate o…
Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.
Predict persona performance in specific task contexts.
Design user-facing agent experts for adaptive UX and personalization. Use when building product features that learn from user behavior, creating per-user expertise files, or implementing AI-driven per…
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.
Qwen Training Data Miner (Prototype)