Skill UI

Build usage analytics and reporting pipelines for Kling AI, combining event collection, aggregation, cost analysis, dashboards, and alerts to monitor generation activity and export CSV-ready data for downstream review.

Automates Neon serverless Postgres workflows via the Composio MCP, letting you list projects and branches, inspect databases, manage roles, and retrieve connection URIs for pipelines and tooling integrations.

Expert in designing and implementing advanced Retrieval-Augmented Generation (RAG) pipelines. This role focuses on optimizing the entire information retrieval process—from document chunking and embedding model selection to vector database architectures and hybrid search strategies. The goal is to bridge the gap between raw knowledge documents and accurate LLM understanding, drastically reducing hallucination and enhancing context relevance for enterprise applications.

This skill provides expertise in building production-grade, scalable data systems and pipelines. It covers the full spectrum of data engineering, including designing robust batch ETL/ELT workflows, implementing real-time streaming architectures (Kafka/Flink), and utilizing modern tools like Airflow, Spark, and dbt. Essential for data architecture design, data lakehouse implementation, and data governance.

Guides building, tuning, and validating production Apache Spark jobs, covering DataFrame/RDD choices, partitioning, broadcast joins, skew handling, caching, and cluster configuration for big data pipelines.

Biopython provides Python APIs for sequence manipulation, database access, BLAST automation, structural bioinformatics, and phylogenetics, making it ideal for scripting custom pipelines and batch processing in computational molecular biology workflows.

Polars is a blazing fast in-memory DataFrame library based on Apache Arrow that replaces pandas for 1-100GB workloads, offering expression-based lazy execution, parallel operators, and rich I/O for ETL pipelines.

PyOpenMS provides Python bindings for OpenMS to drive complete mass spectrometry workflows, covering data IO, spectral processing, feature/peptide-protein identification, quantitation, and metabolomics pipelines.

Apify Actorization is a process that transforms existing, standalone software or scripts (like CLI tools) into standardized, reusable serverless applications called Actors. Actors are packaged as Docker images, accepting structured JSON inputs and producing structured JSON outputs. This skill guides developers on migrating projects to the Apify platform, ensuring compatibility, and enabling scalable, event-driven data processing pipelines.

Guides static reviews of GitHub Actions workflows that invoke AI coding agents, teaching how to find workflow files, trace composite actions, capture security-relevant settings, and detect attacker-controlled data paths to agents in CI/CD pipelines.

Quick fp-ts reference outlining how to use pipe for transforming specific values and flow for creating reusable transformation pipelines, with examples covering Option and Array utilities for chained data processing.

A comprehensive suite of 25 advanced agent skills designed for modern software development and platform operations. These tools cover the entire development lifecycle, including multi-agent architecture design, robust CI/CD pipelines, database schema management, performance profiling, observability setup, and security auditing. Ideal for complex system integration and platform engineering teams.