Total 50,706 skills, AI & Machine Learning has 8496 skills
Showing 12 of 8496 skills
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server.
Enhance text storyboards into Seedance 2.0 video prompts one by one. Call this when the text storyboard is completed and needs to be converted into executable video prompts.
Create wrapper skills that call remote tools through UXC. Use when defining a new provider skill and you need reusable templates, validation rules, and anti-pattern guidance based on proven UXC skill practices.
Lossless DFlash speculative decoding for MLX on Apple Silicon — 1.7–4x faster LLM inference using block diffusion drafting with target model verification.
Adaptive exploration pipeline that integrates /brainstorm, /think, and /red-team with intelligent pivoting. Unlike /deepthink (which takes a fixed idea and iterates), /prospect starts with divergent brainstorming, picks the most promising vein, runs deep analysis, and — crucially — can PIVOT back to divergent thinking when: the idea dies under red-team, an adjacent opportunity surfaces during analysis, or the research reveals the real opportunity is elsewhere. Produces a prospecting report: the landscape explored, veins assayed, pivots taken, and the final stake with conviction. Use when the user says "prospect", "explore this space", "find opportunities", "what should I build", "explore and analyze", or has a domain/trend they want to both explore AND evaluate.
3-에이전트(Architect→Builder→Reviewer) 루프로 단일 기능을 설계·구현·검증하는 팀 스킬. "3a로 만들어줘", "3에이전트", "설계-구현-검토", "team-3a" 키워드로 트리거. peach-team보다 가벼운 단일 기능·소규모 수정에 적합.
Guides systematic PyTorch recommender-system model development across compact data facts, existing source code, configs, focused tests, and training loops without overloading context from broad research archives. Use when building, debugging, or refactoring torch/nn.Module RecSys models with Transformer/HSTU/attention blocks, sparse/dense/list feature fusion, pCVR/CTR heads, ablation axes, or competition codebases where many model ideas exist but bugs and interface drift must be controlled. 用来指导推荐系统 PyTorch 模型开发、Transformer/HSTU 建模、关键数据事实、特征交互、shape/debug、训练闭环和已有模型结构的系统化推进。
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.