Agent Skills Hub

training-data-curation

Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.

wenxian

Automated academic literature retrieval, structured summarization, and multi-channel scheduling workflow for research topics.

github-workflow-automation

AI-driven GitHub Actions automation featuring swarm-based workflow orchestration, intelligent CI/CD pipeline management, and autonomous repository maintenance.

k8s-troubleshooter

Systematic Kubernetes troubleshooting, pod diagnostics, cluster health monitoring, and incident response playbooks.

root-cause-tracing

Systematic debugging skill to trace errors backward through call stacks, identify original triggers, and implement layered defenses instead of patching symptoms.

performance-testing

Profiles application performance using k6, Artillery, or JMeter to measure latency, throughput, and error rates. Ideal for planning load, stress, and soak tests to identify bottlenecks.

outpost

Open-source infrastructure for reliable, multi-destination event delivery. Route webhooks to HTTP, SQS, RabbitMQ, Pub/Sub, EventBridge, or Kafka with built-in retries and observability.

data_processor

A multi-paradigm ETL pipeline agent supporting batch and streaming data processing, schema inference, and configurable DAG-based transformations for heterogeneous data sources.

swiftui-expert-skill

Expert SwiftUI development assistant: refactor code, improve performance, and diagnose app hitches or CPU issues using Xcode Instruments trace analysis.

error-handling

Implement robust backend error handling with custom classes, middleware, structured logging, and recovery patterns.

ops-devops-platform

DevOps and platform engineering patterns: Kubernetes, Terraform, GitOps, CI/CD, observability, incident response, and cloud-native ops.

new-analyzer

Guide for implementing a new AI coding agent analyzer in Splitrail to track token usage, costs, and performance metrics.