Claude Skills

Manage multiple Claude Code instances across git worktrees. Check status, claim/release file locks, sync decisions, and prevent conflicts. Use when coordinating multiple worktrees or Claude instances.

Use when assessing task complexity, before starting complex tasks, or when stuck after multiple attempts. Provides quality-gates scoring (1-5) and escalation workflows.

Query decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implementing multi-hop retrieval, or improving coverage for compound questions.

Radix UI unstyled accessible primitives for dialogs, popovers, dropdowns, and more. Use when building custom accessible components, understanding shadcn internals, or needing polymorphic composition.

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.

Value Proposition Canvas, Jobs-to-be-Done (JTBD), Build/Buy/Partner decisions, and strategic product frameworks. Use when validating value propositions, understanding customer needs, or making strategic technology decisions.

Use when building secure AI pipelines or hardening LLM integrations. Defense-in-depth implements 8 validation layers from edge to storage with no single point of failure.

CSS Scroll-Driven Animations with ScrollTimeline, ViewTimeline, parallax effects, and progressive enhancement for performant scroll effects. Use when implementing scroll-linked animations or parallax.

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.

Responsive design with Container Queries, fluid typography, cqi/cqb units, and mobile-first patterns for React applications. Use when building responsive layouts or container queries.

High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.

React render performance patterns including React Compiler integration, memoization strategies, TanStack Virtual, and DevTools profiling. Use when debugging slow renders, optimizing large lists, or reducing unnecessary re-renders.

Reranking patterns for improving search precision. Use when implementing cross-encoder reranking, LLM-based relevance scoring, or improving retrieval quality in RAG pipelines.

Message queue patterns with RabbitMQ, Redis Streams, and Kafka. Use when implementing async communication, pub/sub systems, event-driven microservices, or reliable message delivery.

Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.

OrchestKit health diagnostics command that validates plugin configuration and reports issues. Use when running doctor checks or troubleshooting plugin health.

Use when building secure AI pipelines or hardening LLM integrations. Defense-in-depth implements 8 validation layers from edge to storage with no single point of failure.

Use this skill when creating or evolving design systems for applications. Provides design token structures, component architecture patterns, documentation templates, and accessibility guidelines. Ensures consistent, scalable, and accessible UI design across products.

[QUALITY] Assess task complexity with codebase metrics. Use when determining if a task needs breakdown.

RFC 9457 Problem Details for standardized HTTP API error responses. Use when implementing problem details format, structured API errors, error registries, or migrating from RFC 7807.

Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.

Event sourcing patterns for storing state as a sequence of events. Use when implementing event-driven architectures, CQRS, audit trails, or building systems requiring full history reconstruction.

Use when completing tasks, code reviews, or deployments to verify work with evidence. Collects test results, build outputs, coverage metrics, and exit codes to prove work is complete.

Deep codebase exploration with parallel specialized agents. Use when exploring a repo, finding files, or discovering architecture with the explore agent.