Skill UI

This guide provides robust, production-ready strategies for integrating with the PostHog API. It teaches developers how to handle API rate limits (429 errors) gracefully using exponential backoff and retry logic. Furthermore, it covers implementing request queuing for burst protection, optimizing with data caching, and monitoring rate limit headers, ensuring stable and reliable data ingestion regardless of traffic volume.

A comprehensive guide to implementing production-ready patterns for PostHog analytics integration. This includes establishing singleton clients for both server-side (Python/Node) and client-side environments. It provides type-safe event capture utilities, React hooks for handling feature flags (including variants), and the full Next.js App Router setup for robust pageview tracking. Patterns are available for both TypeScript/JavaScript and Python environments.

This guide outlines best practices for securing PostHog API keys. It differentiates between low-risk Project keys and high-privilege Personal keys, detailing methods for implementing least-privilege access, scoped key creation, secure rotation procedures, and leak prevention using environment variables, pre-commit hooks, and server-side isolation.

This comprehensive guide teaches the best practices for writing effective, blameless postmortem reports following technical incidents. It provides a structured approach to documenting timelines, conducting root cause analysis (RCA), identifying systemic failures, and creating actionable follow-up items. Mastering this skill is crucial for fostering organizational learning and preventing future service disruptions.

A comprehensive guide covering critical pitfalls and best practices for writing robust PowerShell scripts on Windows. It details essential rules for operator syntax (parentheses), safe path handling, null checking, advanced error management (try/catch), and correct JSON serialization, ensuring your automation code is highly reliable and maintainable.

Prediction Monitor Assistant automates machine learning deployment monitoring tasks, offering step-by-step guidance, best-practice patterns, production-ready code and configuration generation, and validation to keep serving and inference workflows reliable.

This skill provides a comprehensive pattern for optimizing bulk API interactions. It enables efficient processing of large arrays of operations by supporting both synchronous (for small batches) and asynchronous (for large batches) execution. Key features include concurrency control, robust partial failure handling, progress tracking via background workers, and dedicated validation steps, ensuring reliable data throughput for high-volume requests.

Enables Claude to invoke the computer-vision-processor plugin, auto-generating Python calls to run object detection, classification, and segmentation on user-provided images for detailed analysis.

Coordinate Productlane operations through Rube MCP and Composio tooling, covering discovery, connection checks, execution, bulk workbench runs, and schema adherence so dynamic integrations stay reliable.

Automates Project Bubble workflows via Rube MCP and Composio toolkits, emphasizing schema discovery, connection checks, and multi-tool execution for reliable project ops.

Covers prompt and response caching plus Cache Augmented Generation patterns for LLMs such as Claude and OpenAI to reuse stable context, reduce repeat work, and cut latency/cost on recurring queries.

Document describes structured prompts, chain-of-thought guidance, few-shot examples, system prompt design, and tooling advice for building reliable prompt engineering workflows in LLM-augmented products.