Machine Learning Skills

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Search the web for real-time information using the Skywork web search API. Use this skill whenever the user needs up-to-date information from the internet — for example, researching a topic, looking up recent events, finding facts or statistics, gathering material for a document or presentation, or answering questions that require current data. Also trigger when the user says things like "search for", "look up", "find information about", "what's the latest on", or any request that implies needing information beyond your training data.

A prompt repetition technique for improving LLM accuracy. Achieves significant performance gains in 67% (47/70) of 70 benchmarks. Automatically applied on lightweight models (haiku, flash, mini).

Turn JSON or PostgreSQL jsonb payloads into compact readable context for LLMs. Use when a user wants to compress JSON, reduce token usage, summarize API responses, or convert structured data into model-friendly text without dumping raw paths.

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Evaluate JavaScript at bundle time and inline results. Use when optimizing compile-time code generation, embedding files, inlining environment variables, or executing code during the bundling process.

Generate output schemas (dataset_schema.json, output_schema.json, key_value_store_schema.json) for an Apify Actor by analyzing its source code. Use when creating or updating Actor output schemas.

>- Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it does not touch on-canvas evaluation nodes.

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

Query PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics. Use when users ask about CI duration, job failures, queue times, workflow trends, runner health, dashboard data, or PyTorch infrastructure metrics.

Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or AT_DISPATCH_INDEX_TYPES, and when considering binary-size or performance impact of index-type templating.

Write Metal/MPS kernels for PyTorch operators. Use when adding MPS device support to operators, implementing Metal shaders, or porting CUDA kernels to Apple Silicon. Covers native_functions.yaml dispatch, host-side operators, and Metal kernel implementation.

Fix bugs reported in PyTorch GitHub issues by reproducing, root-causing, and implementing a fix in the local working tree. Use when the user asks to fix a PyTorch GitHub issue.

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.

| Train custom AI models (LoRA) on fal.ai for personalized image generation tailored to a brand, character, or style.

>- Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the privacy/cost/offline trade-offs. Based on Lesson 17 of AI Agents for Beginners. Qwen function calling, local tool calling, local RAG, Chroma vector database, local MCP server, privacy-preserving agent, hybrid local and cloud agent, small language model agent, engineering assistant on my machine. Lesson 16), building your first agent concept (Lesson 01), Foundry (cloud) hosted agents, GPU cluster / server-side inference provisioning.

Bumuo ng mga local-first AI agents na tumatakbo nang buong-buo sa isang developer workstation gamit ang Microsoft Foundry Local at Qwen function-calling models. Saklaw nito ang Small Language Models (SLMs), ang OpenAI-compatible na lokal na endpoint, sandboxed local tools, lokal na RAG gamit ang Chroma, lokal na MCP servers, hybrid cloud/local routing, at ang privacy/cost/offline trade-offs. Batay nang lokal, offline agent, on-device agent, Foundry Local, Qwen function calling, local tool calling, lokal na RAG, Chroma vector database, lokal na MCP server, privacy-preserving agent, hybrid local at cloud agent, small language model agent, engineering assistant (gamitin ang deploying-scalable-agents / Lesson 16), paggawa ng iyong unang agent concept (Lesson 01), Foundry (cloud) hosted agents, GPU cluster / server-side inference provisioning.'

Cherry Studio 产品知识库、源码路径索引、故障排查和页面导航。当用户询问 Cherry Studio 的功能、配置、报错、使用方法时触发。也适用于用户提到 provider、模型、知识库、Agent、MCP、OpenClaw、PDF、快捷短语等关键词的场景。

Create test datasets (hits, visits, tpcds, tpch) from standard scripts. Ensures the server is running first.

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.

Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.

Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.

Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.

Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.

Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training configuration, choosing rank/alpha/target modules, or deciding between LoRA, QLoRA, and full fine-tuning.

Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.

Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning.

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced X For You algorithm. Use when building any system that picks "the top K items for a (user, context)" — content feeds, search ranking, RAG rerankers, task prioritizers, notification triage, ad selection.

Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.

Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Produces clickable URLs for sharing Arize resources with team members. Use when the user wants to link to or open a trace, span, session, dataset, evaluator, or annotation config in the Arize UI.

> Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.

Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user asks for a competitive landscape, competitor analysis, peer comparison, market positioning assessment, strategic review, or investment memo deck. Also triggers on "who are the competitors to X", "benchmark X against peers", "build a market map", or any request to systematically evaluate competitive dynamics across an industry.

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.

Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.

Read, inspect, and write Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. Use for low-level FCS metadata and channel inspection, NumPy event extraction, multi-dataset files, table export, and FCS 3.1 creation; use FlowKit for compensation, cytometry transforms, gating, or FlowJo workspaces.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extraction, and stain normalization for H&E images. Best for simple pipelines, dataset preparation, and quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.