Loading...
Loading...
Found 173 Skills
Evidence-based Drug-Drug Interaction (DDI) assessment skill modeled after the Micromedex Drug-Reax methodology. Trigger this skill whenever the user types /drug-drug, mentions "drug interaction", "DDI", "drug-drug", "can I take X with Y", "interaction between", "交互作用", "併用", or asks whether two medications can be used together. This skill performs systematic literature retrieval via PubMed, CrossRef, and WebSearch, then produces a structured assessment report with Severity, Documentation, Onset, Mechanism, Clinical Effects, and Management — mirroring the Micromedex Drug-Reax classification framework. Even casual questions like "is it safe to combine A and B" should trigger this skill.
Authoring MSW scripts (.mlua) plus integrated playtest and debugging. Covers mlua syntax, annotations (@Component/@Logic/@ExecSpace/@Sync), lifecycle, exec spaces, property sync, event system, file workflow, build-log inspection, error classification, and the test/debug loop. Keywords: script, mlua, lua, Component, Logic, annotation, ExecSpace, Sync, event, play, test, debug, lifecycle.
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include "RCA on my ChangeNet model", "why is my AOI model failing", "audit ChangeNet predictions", "investigate FAR regressions", "root cause analysis on visual-changenet".
Multi-source AI news aggregation and digest generation with deduplication, classification, and source tracing. Supports 20+ sources, 5 theme categories, multi-language output (ZH/EN/JA), and image export.
Chain multiple AI steps into one reliable pipeline. Use when your AI task is too complex for one prompt, you need to break AI logic into stages, combine classification then generation, do multi-step reasoning, build a compound AI system, orchestrate multiple models, or wire AI components together. Powered by DSPy multi-module pipelines.
Multimodal media authentication and deepfake forensics. PRNU analysis, IGH classification, DQ detection, semantic forensics, and LLM-augmented sensemaking for the post-empirical era. Use when working with deepfake, media forensics, fake detection, synthetic media, prnu, image authentication, video verification, disinformation.
Identifies subdomains and suggests bounded contexts in any codebase following DDD Strategic Design. Use when analyzing domain boundaries, identifying business subdomains, assessing domain cohesion, mapping bounded contexts, or when the user asks about DDD strategic design, domain analysis, or subdomain classification.
Use this when the Discover (reverse engineering) of legacy projects tends to get out of control in coverage. You need to first conduct module classification (P0/P1/P2) and constrain the depth of reverse engineering, ensuring that high-ROI modules are made traceable first instead of "writing everything but making it unmaintainable."
[WHAT] Universal content intake system for URLs (GitHub repos, YouTube videos, articles, PDFs) and skill packages (skills.sh, skill:// protocol) [HOW] Phase 1: Clone repos/fetch transcripts/scrape content/resolve skills to ~/lev/workshop/intake/. Phase 2-3: Load workshop/intake.md for full analysis [WHEN] Use when user provides a URL to analyze, says "intake/download", wants to evaluate external content, or references a skill package [WHY] Systematically evaluates external content and skill packages for adoption/adaptation with tier classification and ADR creation Triggers: "intake", "download", "analyze this url", "check out this repo", "review this video", "evaluate content", "install skill", "skill://"
Resolve merge conflicts systematically with context-aware 3-tier classification and escalation protocol
Use when the user mentions document parsing, PDF extraction, OCR, markdown extraction, structured data extraction from documents, document classification/splitting, LandingAI, ADE API, or wants to pull data out of a PDF/image/spreadsheet
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.