Total 51,080 skills, AI & Machine Learning has 8556 skills
Showing 12 of 8556 skills
Create custom multi-agent workflows for Atomic CLI using the defineWorkflow() session-based API with programmatic SDK code. Use this skill whenever the user wants to create a workflow, build an agent pipeline, define a multi-stage automation, set up a review loop, or connect multiple coding agents together. Also trigger when they mention workflow files, .atomic/workflows/, defineWorkflow, or ask how to automate a sequence of agent tasks — even if they don't use the word "workflow" explicitly.
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
Google Model Armor: Create a new Model Armor template.
>
Set up Symphony (OpenAI's Codex orchestrator) for a user's repo. Use when the user mentions Symphony setup, configuring Symphony, getting Symphony running, or wants to connect their repo to Linear for autonomous Codex agents. Also use when the user says "set up symphony", "configure symphony for my repo", or references WORKFLOW.md configuration.
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.
Search, install, and publish skills. Use search_skills tool for discovery + auto-install. Manual publish via gateway.
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
Help users create and run AI evaluations. Use when someone is building evals for LLM products, measuring model quality, creating test cases, designing rubrics, or trying to systematically measure AI output quality.
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.