Claude Skills

Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using agent-browser CLI. Use when capturing browser content, extracting web data, saving page content.

LangGraph conditional routing patterns. Use when implementing dynamic routing based on state, creating branching workflows, or building retry loops with conditional edges.

LangGraph state management patterns. Use when designing workflow state schemas, using TypedDict vs Pydantic, implementing accumulating state with Annotated operators, or managing shared state across nodes.

gRPC with Python using grpcio and protobuf for high-performance microservice communication. Use when implementing service-to-service APIs, streaming data, or building polyglot microservices requiring strong typing.

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

DDD aggregate design patterns for consistency boundaries and invariants. Use when designing aggregate roots, enforcing business invariants, handling cross-aggregate references, or optimizing aggregate size.

Best practices for HeyGen - AI avatar video creation API. Use when creating AI avatar videos, generating talking head videos, or integrating HeyGen with Remotion.

[CONFIG] Configure OrchestKit settings. Use when customizing MCP servers, plugin options, or preferences.

Performance and load testing with k6 and Locust. Use when validating system performance under load, stress testing, identifying bottlenecks, or establishing performance baselines.

Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.

Advanced MCP patterns for tool composition, resource management, and scaling. Build custom MCP servers, compose tools, manage resources efficiently. Use when composing MCP tools or scaling MCP servers.

[GIT] Creates commits with conventional format and validation. Use when committing changes or generating commit messages.

Assess task complexity with automated codebase metrics. Use before starting work to determine if task needs breakdown.

Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.

LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.

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

ROI, NPV, IRR, payback period, and total cost of ownership analysis for investment decisions. Use when building financial justification for projects, evaluating SaaS investments, or comparing alternatives.

Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using agent-browser CLI. Use when capturing browser content, extracting web data, saving page content.

Vercel agent-browser CLI for headless browser automation. 93% less context than Playwright MCP. Snapshot + refs workflow with @e1 @e2 element references. Use when automating browser tasks, web scraping, form automation, or content capture.