Results for “learning”

Capture durable project memory from work, debates, debugging discoveries, learned conventions, deferred options, and session outcomes. Load when the user says remember this, save this learning, record what happened, update project memory, or preserve context for future agents.

Authors or reviews Know/Understand/Do charts for competency-based learning targets across developmental bands. Handles seven input types from raw curriculum documents to existing LT sets. Routes to upstream skills when stronger inputs are available.

Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Run machine learning and generative AI tasks directly in BigQuery SQL using built-in functions for forecasting, anomaly detection, key driver analysis, and text generation.

Run TAO SDK jobs as Docker containers on a local or remote Docker daemon with NVIDIA GPU support, including preflight checks and credential handling.

Train, evaluate, export, and run inference on TAO action-recognition models for classifying temporal actions in video clips using RGB, optical flow, or joint input.

Generates a structured HTML prep file for the next working day by pulling calendar data via WorkIQ, classifying meetings, detecting conflicts, finding learning and deep-work slots, and providing productivity recommendations.

Interactive training for the GitHub Copilot CLI with guided lessons, quizzes, scenario challenges, and a full reference covering slash commands, shortcuts, modes, agents, skills, MCP, and configuration.

Process and analyze large tabular datasets (billions of rows) that exceed available RAM using lazy, out-of-core DataFrames with fast aggregations, visualization, and machine learning integration.

Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features and classifying samples with machine learning models.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Use when detecting, responding to, or recovering from system failures, outages, security breaches, or critical errors. This skill provides a structured incident response process for any type of failure, ensuring consistent handling, communication, and post-incident learning.

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Guides LLM post-training with RL using slime, a Megatron+SGLang framework for training GLM, Qwen, DeepSeek, and Llama models with GRPO, async, and multi-turn workflows.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Guide for defining and using Claude subagents effectively. Use when (1) creating new subagent types, (2) learning how to delegate work to specialized subagents, (3) improving subagent delegation prompts, (4) understanding subagent orchestration patterns, or (5) debugging ineffective subagent usage.

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.

Turns folders, codebases, websites, PDFs, documents, and research topics into source-grounded HTML documents, narrated videos, or learning courses; publishes and revises collaborative HTML pages via CLI, REST API, and MCP server.

Convert chemical structures (SMILES or RDKit molecules) into numerical representations for machine learning, covering 100+ featurizers including ECFP, MACCS, descriptors, and pretrained models like ChemBERTa, with support for QSAR modeling and virtual screening.

Design a single-point rubric with one criterion and open columns for evidence. Use for student self-assessment, peer feedback, teacher formative feedback, or pre-task planning. Works with any learning target, with or without a band system.

Promote project-specific memories into strict, small global memory only when they are cross-project, stable, useful, safe, and worth the global context cost. Load when the user says make this global, remember across projects, save this globally, or promote this learning.

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, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Deploys anomaly detection for industrial control environments using machine learning models trained on OT network baselines, physics-based process models, and behavioral analysis of industrial protocol communications.

Scales machine learning training from single GPU to multi-node clusters with minimal code changes. Supports PyTorch, TensorFlow, and HuggingFace with built-in hyperparameter tuning, fault tolerance, and elastic scaling.

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.

Builder of knowledge products such as courses, ebooks, guides, memberships, and educational assets. Use for course creation, ebook writing, guide development, membership design, curriculum building, learning materials, or when the user asks for the Knowledge Executor, educational content, or knowledge products.

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.

Deploy AI and NLP-powered detection systems to identify business email compromise attacks by analyzing writing style, behavioral patterns, and contextual anomalies that evade traditional rule-based filters.

Prepare for tomorrow's meetings and tasks. Pulls calendar from Outlook via WorkIQ, cross-references open tasks and workspace context, classifies meetings, detects conflicts and day-fit issues, finds learning and deep-work slots, and generates a structured HTML prep file with productivity recommendations.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Use before starting any new work to check for existing knowledge. This skill provides a systematic search and retrieval process for finding relevant knowledge from memory systems (PARA, Gigabrain, OpenStinger, existing skills) before starting work, preventing redundant effort and leveraging prior learning.