Search Skills

Creates new technical blog posts for the Artsy Engineering blog, enabling structured content writing and publishing.

Validates TUI output using visual (PNG/SVG) and semantic (LLM) validation modes.

Lists repository code tasks with status, dates, and metadata for tracking pending work and task discovery.

Generates comprehensive codebase documentation including architecture, components, and workflows in structured metadata files for AI assistant understanding.

Generates structured code task files from descriptions or PDD plans following Amazon's code task format with sequential step processing.

Persists project-specific codebase context to aid architectural decisions, pattern recognition, and recurring problem-solving across sessions.

Creates and manages Ralph hat collection presets, designs multi-agent workflows, and integrates new hats into existing configurations.

Guides code implementation using test-driven development (TDD) principles, generating test cases and idiomatic code while adhering to existing patterns.

Validates hat collection preset configurations and audits the preset library for bugs and UX issues.

EvalKit enables conversational creation, execution, and analysis of AI agent evaluations via the Strands Evals SDK.

Manages runtime tasks and memory states during Ralph orchestration execution, ensuring seamless workflow coordination.

Guides users to transform rough ideas into detailed design documents and implementation plans using Prompt-Driven Development methodology.

Creates animated terminal demos as GIFs or SVGs from asciinema recordings for embedding in GitHub documentation and pull requests.

Automates version increment for ralph-orchestrator releases after code fixes are committed and ready for publication.

Automates extending OpenTelemetry instrumentation for MCP Gateway, analyzing code changes and ensuring standards compliance via implementation and documentation.

Automates creation of clear, descriptive commit messages from Git diffs to improve version control communication and code review efficiency.

Benchmarking indicator performance with BenchmarkDotNet for regression detection, optimization patterns, and targeted speed improvements (1.5x Series, 1.2x BufferList).

Implements real-time indicators with O(1) performance for streaming systems, covering provider selection, RollbackState patterns, and StreamHubTestBase testing.

Generates code for indicator catalog entries, enabling automation via Catalog.cs, CatalogListingBuilder, and PopulateCatalog registration patterns.

Provides efficient state management for incremental indicators using BufferList, covering interface implementation and testing patterns for IIncrementFromChain and IIncrementFromQuote.

Provides a quality gates checklist to ensure code meets standards before finalizing implementation cycles.

Implements precise batch indicators for StaticSeries, ensuring mathematical accuracy and performance optimization as the canonical reference for all implementations.

Standardizes testing conventions for stock indicators including FluentAssertions patterns, naming, and precision requirements.

Comprehensive tool for evaluating technology stacks with TCO analysis, security assessment, and AI-driven recommendations for engineering teams.