Loading...
Loading...
Found 200 Skills
Detects and redacts Personally Identifiable Information (PII) like emails, phone numbers, and credit cards. Use when cleaning logs, datasets, or communications to comply with GDPR/CCPA privacy standards.
Resolves shared ecosystem environment constants (HuggingFace credentials, dataset repo IDs, project root path) for any plugin without depending on internal shared libraries. V2 enforces Token Leakage constraints.
Use ONLY when creating NEW registrable components in ML projects that require Factory/Registry patterns. ✅ USE when: - Creating a new Dataset class (needs @register_dataset) - Creating a new Model class (needs @register_model) - Creating a new module directory with __init__.py factory - Initializing a new ML project structure from scratch - Adding new component types (Augmentation, CollateFunction, Metrics) ❌ DO NOT USE when: - Modifying existing functions or methods - Fixing bugs in existing code - Adding helper functions or utilities - Refactoring without adding new registrable components - Simple code changes to a single file - Modifying configuration files - Reading or understanding existing code Key indicator: Does the task require @register_* decorator or Factory pattern? If no, skip this skill.
Use Fabric CLI for Power BI operations — semantic models, reports, DAX queries, refresh, gateways. Activate when users work with Power BI items, need to refresh datasets, execute DAX, manage reports, or troubleshoot refresh failures.
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.
XAF Memory Leak Prevention - event handler symmetry (OnActivated/OnDeactivated/Dispose), ObjectSpace scoped disposal with using statement, batch processing large datasets, IDisposable pattern for controllers with List<IDisposable> tracker, WeakEventSubscription, static reference anti-patterns, CollectionSource disposal, Session/HttpContext/Application anti-patterns (WebForms), ObjectSpacePool, controller lifecycle tracking, NavigationMonitor, warning signs, diagnostic tools (dotMemory, PerfView, XAF Tracing). Use when diagnosing memory leaks, auditing controller disposal, reviewing ObjectSpace lifetime, or reviewing Session usage in DevExpress XAF applications.
Instrument, trace, evaluate, and monitor LLM applications and AI agents with LangSmith. Use when setting up observability for LLM pipelines, running offline or online evaluations, managing prompts in the Prompt Hub, creating datasets for regression testing, or deploying agent servers. Triggers on: langsmith, langchain tracing, llm tracing, llm observability, llm evaluation, trace llm calls, @traceable, wrap_openai, langsmith evaluate, langsmith dataset, langsmith feedback, langsmith prompt hub, langsmith project, llm monitoring, llm debugging, llm quality, openevals, langsmith cli, langsmith experiment, annotate llm, llm judge.
Design and architect Goldsky Turbo pipelines. Use this skill for 'should I use X or Y' decisions: kafka source vs dataset source, streaming vs job mode, which resource size (xs/s/m/l/xl/xxl) for my workload, postgres vs clickhouse vs kafka sink, fan-in vs fan-out data flow, one pipeline vs many, dynamic table vs SQL join, how to handle multi-chain deployments. Also use when the user asks 'what's the best way to...' for a pipeline design problem, or is unsure how to structure their pipeline before building it.
Production-ready single-cell and expression matrix analysis using scanpy, anndata, and scipy. Performs scRNA-seq QC, normalization, PCA, UMAP, Leiden/Louvain clustering, differential expression (Wilcoxon, t-test, DESeq2), cell type annotation, per-cell-type statistical analysis, gene-expression correlation, batch correction (Harmony), trajectory inference, and cell-cell communication analysis. NEW: Analyzes ligand-receptor interactions between cell types using OmniPath (CellPhoneDB, CellChatDB), scores communication strength, identifies signaling cascades, and handles multi-subunit receptor complexes. Integrates with ToolUniverse gene annotation tools (HPA, Ensembl, MyGene, UniProt) and enrichment tools (gseapy, PANTHER, STRING). Supports h5ad, 10X, CSV/TSV count matrices, and pre-annotated datasets. Use when analyzing single-cell RNA-seq data, studying cell-cell interactions, performing cell type differential expression, computing gene-expression correlations by cell type, analyzing tumor-immune communication, or answering questions about scRNA-seq datasets.
Comprehensive guide for AntV L7 geospatial visualization library. Use when users need to: (1) Create interactive maps with WebGL rendering (2) Visualize geographic data (points, lines, polygons, heatmaps) (3) Build location-based data dashboards (4) Add map layers, interactions, or animations (5) Process and display GeoJSON, CSV, or other spatial data (6) Integrate maps with AMap (GaodeMap), Mapbox, Maplibre, or standalone L7 Map (7) Optimize performance for large-scale geographic datasets
Implement and extend PostHog Data warehouse import sources. Use when adding a new source under posthog/temporal/data_imports/sources, adding datasets/endpoints to an existing source, or adding incremental sync support, pagination, credentials validation, and source tests.
Deterministic 3-phase GitHub PR review comment extraction: Authenticate, Mine, Validate. Use when mining tribal knowledge from PR reviews, extracting coding standards from review history, or building datasets for the Code Archaeologist agent. Use for "mine PRs", "extract review comments", "tribal knowledge", or "PR review history". Do NOT use for analyzing patterns, generating rules, or interpreting comments — that is the Code Archaeologist agent's responsibility.