ETL & Pipelines
- orchestra-research BundleNemo Curator
GPU-accelerated data curation for LLM training, supporting text, image, video, and audio with fuzzy deduplication, quality filtering, semantic deduplication, PII redaction, and NSFW detection.
Audited 14.5k - lingxling BundleScanpy
Performs Scanpy single-cell RNA-seq QC, normalization, HVG selection, PCA/UMAP/t-SNE, clustering, exploratory marker ranking, pseudobulk preparation, visualization, and Seurat or SingleCellExperiment RDS conversion to h5ad. Applies to established exploratory scRNA-seq workflows with explicit count and expression provenance; complementary skills cover scvi-tools models and AnnData format details.
331 - mocchalera SkillExport Premiere
Exports a timeline.json as a Premiere Pro editor packet, including FCP7 XML, captions, and media, with verification steps.
5 - lucaspmarie-a11y SkillPolars
Process in-memory datasets with Polars' expression API, lazy evaluation, and parallel execution, including pandas migration patterns and I/O for CSV, Parquet, and JSON.
Audited 5 - affaan-m SkillData Scraper Agent
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions.
303k - nvidia BundleDeepstream Sop
Build, deploy, evaluate, debug, and measure latency for a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection and VLM classification.
23k - github SkillBigquery Pipeline Audit
Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness, returning a structured report with exact patch locations.
Audited 41.2k - jeffallan BundleMl Pipeline
Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking, creates orchestration DAGs, builds feature store schemas, deploys model registries, and automates retraining and validation workflows.
Audited 12.4k - jorcan BundleDatabase
Guides database design, implementation, optimization, migration, pipeline development, quality, and operations across SQL and NoSQL platforms.
Audited 0 - lucaspmarie-a11y SkillDatabase
Guides database design, implementation, optimization, migrations, data pipelines, and operations across SQL and NoSQL platforms.
Audited 5 - composiohq SkillDatagma Automation
Automate Datagma operations through Composio's Datagma toolkit via Rube MCP, with tool discovery and connection management.
79.5k - composiohq SkillScrape Do Automation
Automate web scraping and data extraction tasks using the Scrape Do toolkit via Rube MCP and Composio.
79.5k - composiohq SkillStormglass Io Automation
Automate Stormglass IO operations through Composio's Stormglass IO toolkit via Rube MCP, including tool discovery, connection management, and execution.
79.5k - k-dense-ai BundleDask
Scale pandas and NumPy workflows to larger-than-memory datasets using parallel and distributed computing.
Audited 57.3k - k-dense-ai BundlePolars
Process data with high-performance DataFrames using Polars' expression-based API, lazy evaluation, and parallel execution for ETL, analytics, and pandas migration.
Audited 57.3k - k-dense-ai BundlePacsomatic
Validates inputs, generates samplesheets and launch scripts, and optionally executes nf-core/pacsomatic matched tumor-normal workflows from BAM files, supporting local runs and scheduler submission (LSF/Slurm/PBS/SGE).
57.3k - k-dense-ai BundleLatchbio Integration
Build and deploy bioinformatics workflows as serverless pipelines on the Latch platform using Python decorators, cloud data management, and GPU support.
Audited 57.3k - k-dense-ai BundleLabarchive Integration
Access and manage LabArchives electronic lab notebooks programmatically via REST API. Create entries, upload attachments, backup notebooks, generate reports, and integrate with Protocols.io, Jupyter, REDCap, and other scientific tools.
57.3k - muratcankoylan BundleBook Sft Pipeline
Convert books into supervised fine-tuning datasets and train style-transfer models that replicate an author's voice.
18.3k - czlonkowski BundleN8n Binary And Data
Handle files and binary data in n8n workflows correctly, covering the $binary vs $json split, reading/writing binary, preserving binary across transforms, and the agent-tool binary boundary.
Audited 6.6k - tradermonty BundleSkill Idea Miner
Extract, score, and backlog skill idea candidates from Claude Code session logs for a weekly skill generation pipeline.
4.7k - tradermonty BundleEdge Concept Synthesizer
Clusters raw detection tickets into reusable edge concepts with thesis, invalidation signals, and strategy playbooks before strategy design.
4.7k - tradermonty BundleEdge Pipeline Orchestrator
Coordinate multi-stage edge research pipelines from candidate detection through strategy design, review, revision, and export.
4.7k - iamanacarolinarezende SkillDatabase
Guides database design, implementation, query optimization, migrations, data pipeline development, and operations across SQL and NoSQL platforms.
Audited 0 - composiohq SkillListclean Automation
Automates Listclean data-cleaning operations through Composio's toolkit via Rube MCP, with tool discovery and connection management.
79.5k - browser-act BundleWebcrawler Deep Crawl
Deep-crawl any website from start URLs, returning per-page LLM-ready text, markdown, or HTML with metadata and in-scope outbound links.
6.4k - k-dense-ai BundleVaex
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.
Audited 57.3k - orchestra-research BundleRay Data
Process large-scale ML datasets with distributed streaming execution across CPU/GPU, supporting Parquet, CSV, JSON, images, and integration with PyTorch, TensorFlow, and Ray Train.
Audited 14.5k - tradermonty BundleEdge Candidate Agent
Convert daily market observations into structured research tickets and export validated candidate specs for a trading strategy pipeline.
4.7k - agentskillexchange SkillDbt MCP Server
Basic usage or getting-started notes:
61 - bankrbot BundleIndexing
Read and query onchain data using events, The Graph, Dune, Ponder, Multicall3, and WebSocket subscriptions, with guidance on block iteration limitations.
1.2k - k-dense-ai BundleBioservices
Query 40+ bioinformatics services (UniProt, KEGG, ChEMBL, Reactome) with a unified Python interface for cross-database analysis, identifier mapping, and sequence analysis.
57.3k - k-dense-ai BundleZarr Python
Store and process large N-dimensional arrays with chunking, compression, and parallel I/O, integrating with NumPy, Dask, and Xarray for cloud-native scientific computing.
Audited 57.3k - k-dense-ai BundleDnanexus Integration
Build and deploy apps/applets on the DNAnexus cloud genomics platform, manage data objects, run workflows, and use the dxpy Python SDK for genomics pipeline development and execution.
57.3k - jeffallan BundleSpark Engineer
Write, optimize, and debug Apache Spark jobs for high-performance distributed data processing, ETL pipelines, and big data workloads.
Audited 12.4k - browser-act BundleAmazon Asin Lookup API Skill
Extract structured product details from Amazon using an ASIN, including title, price, ratings, brand, and description via the BrowserAct API.
6.4k