Search Skills

Provides a streamlined interface for users to submit feedback, report issues, and suggest improvements to the OrchestKit system.

Provides advanced RAG patterns for agentic pipelines, including Self-RAG, Corrective-RAG, and knowledge graphs for adaptive retrieval and query rewriting.

Provides edge deployment patterns and runtime best practices for Cloudflare Workers, Vercel Edge, and Deno Deploy, focusing on middleware, streaming, and low-latency distribution.

Enforces standardized project structure with feature-based organization, limited nesting, and unidirectional imports to maintain codebase integrity during file creation and architecture reviews.

Enhances semantic retrieval quality using Hypothetical Document Embeddings to align queries with document content, improving RAG performance in ambiguous cases.

Provides standardized implementation for RFC 9457 problem details in HTTP API error responses, ensuring consistent error structures and migration from RFC 7807.

Provides CSS-based scroll-driven animations using ScrollTimeline and ViewTimeline for parallax effects and smooth scroll-linked interactions.

Manages database schema versioning, change tracking, and audit trails across environments for consistent database evolution.

Comprehensive suite for designing, optimizing, and managing AI prompts using Chain-of-Thought, few-shot learning, and versioning to enhance model accuracy and lifecycle management.

Builds Model Context Protocol (MCP) servers to extend Claude's capabilities with custom tools and external integrations for Claude Desktop.

Optimizes React application performance using memoization, virtualization, and profiling to eliminate unnecessary re-renders and accelerate rendering.

Designs efficient database schemas with normalization, indexing, and migration patterns for SQL and NoSQL databases.

Manages a personal best practices library with success/failure pattern tracking to improve decision-making and workflow efficiency.

Automates edge case discovery in code through property-based testing with Hypothesis, validating invariants and data transformations.

Enables real-time token streaming for LLM responses using Server-Sent Events and tool call integration.

Decomposes complex queries into atomic components to improve multi-concept retrieval coverage and accuracy in AI-driven search systems.

Automates WCAG accessibility testing for web applications using axe-core and Playwright, ensuring compliance with accessibility standards.

Generates and manages Architecture Decision Records (ADRs) using the Nygard format, documenting context, decisions, consequences, and alternatives.

Automates GitHub issue status updates using commit activity and sub-task completion, eliminating manual progress tracking.

Provides API rate limiting implementation using token bucket, sliding window, and Redis patterns to handle 429 errors and prevent abuse.

Uses vision-language models for image captioning, document understanding, and visual QA tasks.

Enables async database operations with SQLAlchemy 2.0 using AsyncSession and FastAPI integration for efficient ORM queries and connection pooling.

Optimizes LLM inference performance via vLLM, quantization, and speculative decoding for low latency and high throughput.

Provides React Aria hooks for building WCAG-compliant accessible UI components (buttons, dialogs, menus).