Directorio de skills
Cada recomendación conserva un vínculo claro con su repositorio, auditoría y ruta de instalación.
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Text preprocessing, representation and visualization from zero to hero.
A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.
Build, migrate, theme, drill down, and validate reusable Three.js 3D geographic maps and Earth View entrances for Vue or web dashboards. Use when Codex is asked to create or modify a pure Three.js globe, province-level, all-China, or world 3D maps; transition from an Earth View into the existing China map; switch map boundaries between provinces, country scope, world scope, city scope, or district scope; add hierarchical drilldown from world to country, China to province, province to city, city to district/county; replace GeoJSON, labels, scatter points, fly lines, terrain textures, or chase-light paths; derive a whole map color system from one theme color; or preserve an existing dark HUD-style 3D map visual across new regions.
smart-llm-loader is a lightweight yet powerful Python package that transforms any document into LLM-ready chunks. Spend less time on preprocessing headaches and more time building what matters. From RAG systems to chatbots to document Q&A, SmartLLMLoader handles the heavy lifting so you can focus on creating exceptional AI applications.
A Full Stack ML (Machine Learning) Roadmap involves learning the necessary skills and technologies to become proficient in all aspects of machine learning, including data collection and preprocessing, model development, deployment, and maintenance.
Design and review production-grade low-latency VisionCamera v5 pipelines. Use for real-time GPU, ML, CV, Skia or WebGPU overlays, Nitro frame plugins, zero-copy interop, frame budgets, and latency profiling. Use the general react-native-vision-camera skill for setup, capture, controls, basic frame outputs, or v4 migration.
Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation. Do NOT use for simple text extraction - use pdf-extract for quick reads.
Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated texts
A standardized Python API with necessary preprocessing, machine learning and explainability tools to facilitate graph-analytics in computational pathology.
🔍 Table Extraction Tool: A powerful open-source solution combining OCR and computer vision for extracting structured tabular data from images. Ideal for LLM preprocessing, data analysis, and automation. 🚀
Directorio de skills
Cada recomendación conserva un vínculo claro con su repositorio, auditoría y ruta de instalación.
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Text preprocessing, representation and visualization from zero to hero.
A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.
Build, migrate, theme, drill down, and validate reusable Three.js 3D geographic maps and Earth View entrances for Vue or web dashboards. Use when Codex is asked to create or modify a pure Three.js globe, province-level, all-China, or world 3D maps; transition from an Earth View into the existing China map; switch map boundaries between provinces, country scope, world scope, city scope, or district scope; add hierarchical drilldown from world to country, China to province, province to city, city to district/county; replace GeoJSON, labels, scatter points, fly lines, terrain textures, or chase-light paths; derive a whole map color system from one theme color; or preserve an existing dark HUD-style 3D map visual across new regions.
smart-llm-loader is a lightweight yet powerful Python package that transforms any document into LLM-ready chunks. Spend less time on preprocessing headaches and more time building what matters. From RAG systems to chatbots to document Q&A, SmartLLMLoader handles the heavy lifting so you can focus on creating exceptional AI applications.
A Full Stack ML (Machine Learning) Roadmap involves learning the necessary skills and technologies to become proficient in all aspects of machine learning, including data collection and preprocessing, model development, deployment, and maintenance.
Design and review production-grade low-latency VisionCamera v5 pipelines. Use for real-time GPU, ML, CV, Skia or WebGPU overlays, Nitro frame plugins, zero-copy interop, frame budgets, and latency profiling. Use the general react-native-vision-camera skill for setup, capture, controls, basic frame outputs, or v4 migration.
Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation. Do NOT use for simple text extraction - use pdf-extract for quick reads.
Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated texts
A standardized Python API with necessary preprocessing, machine learning and explainability tools to facilitate graph-analytics in computational pathology.
🔍 Table Extraction Tool: A powerful open-source solution combining OCR and computer vision for extracting structured tabular data from images. Ideal for LLM preprocessing, data analysis, and automation. 🚀
Directorio de skills
Cada recomendación conserva un vínculo claro con su repositorio, auditoría y ruta de instalación.
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Text preprocessing, representation and visualization from zero to hero.
A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.
Build, migrate, theme, drill down, and validate reusable Three.js 3D geographic maps and Earth View entrances for Vue or web dashboards. Use when Codex is asked to create or modify a pure Three.js globe, province-level, all-China, or world 3D maps; transition from an Earth View into the existing China map; switch map boundaries between provinces, country scope, world scope, city scope, or district scope; add hierarchical drilldown from world to country, China to province, province to city, city to district/county; replace GeoJSON, labels, scatter points, fly lines, terrain textures, or chase-light paths; derive a whole map color system from one theme color; or preserve an existing dark HUD-style 3D map visual across new regions.
smart-llm-loader is a lightweight yet powerful Python package that transforms any document into LLM-ready chunks. Spend less time on preprocessing headaches and more time building what matters. From RAG systems to chatbots to document Q&A, SmartLLMLoader handles the heavy lifting so you can focus on creating exceptional AI applications.
A Full Stack ML (Machine Learning) Roadmap involves learning the necessary skills and technologies to become proficient in all aspects of machine learning, including data collection and preprocessing, model development, deployment, and maintenance.
Design and review production-grade low-latency VisionCamera v5 pipelines. Use for real-time GPU, ML, CV, Skia or WebGPU overlays, Nitro frame plugins, zero-copy interop, frame budgets, and latency profiling. Use the general react-native-vision-camera skill for setup, capture, controls, basic frame outputs, or v4 migration.
Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation. Do NOT use for simple text extraction - use pdf-extract for quick reads.
Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated texts
A standardized Python API with necessary preprocessing, machine learning and explainability tools to facilitate graph-analytics in computational pathology.
🔍 Table Extraction Tool: A powerful open-source solution combining OCR and computer vision for extracting structured tabular data from images. Ideal for LLM preprocessing, data analysis, and automation. 🚀
Directorio de skills
Cada recomendación conserva un vínculo claro con su repositorio, auditoría y ruta de instalación.
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Text preprocessing, representation and visualization from zero to hero.
A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.
Build, migrate, theme, drill down, and validate reusable Three.js 3D geographic maps and Earth View entrances for Vue or web dashboards. Use when Codex is asked to create or modify a pure Three.js globe, province-level, all-China, or world 3D maps; transition from an Earth View into the existing China map; switch map boundaries between provinces, country scope, world scope, city scope, or district scope; add hierarchical drilldown from world to country, China to province, province to city, city to district/county; replace GeoJSON, labels, scatter points, fly lines, terrain textures, or chase-light paths; derive a whole map color system from one theme color; or preserve an existing dark HUD-style 3D map visual across new regions.
smart-llm-loader is a lightweight yet powerful Python package that transforms any document into LLM-ready chunks. Spend less time on preprocessing headaches and more time building what matters. From RAG systems to chatbots to document Q&A, SmartLLMLoader handles the heavy lifting so you can focus on creating exceptional AI applications.
A Full Stack ML (Machine Learning) Roadmap involves learning the necessary skills and technologies to become proficient in all aspects of machine learning, including data collection and preprocessing, model development, deployment, and maintenance.
Design and review production-grade low-latency VisionCamera v5 pipelines. Use for real-time GPU, ML, CV, Skia or WebGPU overlays, Nitro frame plugins, zero-copy interop, frame budgets, and latency profiling. Use the general react-native-vision-camera skill for setup, capture, controls, basic frame outputs, or v4 migration.
Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation. Do NOT use for simple text extraction - use pdf-extract for quick reads.
Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated texts
A standardized Python API with necessary preprocessing, machine learning and explainability tools to facilitate graph-analytics in computational pathology.
🔍 Table Extraction Tool: A powerful open-source solution combining OCR and computer vision for extracting structured tabular data from images. Ideal for LLM preprocessing, data analysis, and automation. 🚀