Agent skills for Claude Code

Build voice AI agents with LiveKit Agents SDK.

Build LiveView: async data (assign_async), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for…

Use for Livewire security work. Covers what a public property publishes, snapshot serialization, #[Locked], the persistent middleware gap…

Maintains an implementation-agnostic, behavior-first functional blueprint to guide AI-driven refactoring and long-term project evolution.

Keep a long-lived project's documentation from rotting by assigning existing project docs clear constitution, map, status, and history…

Use when targeting Living Reviews in Relativity (LRR) or deciding whether an invited, continuously updated authoritative review in…

Entry point for deploying and managing apps on Lizard via the `lizard` CLI (npm `@lizard-build/cli`).

Analyzes articles to extract deep structural insights and cognitive collisions using an X-ray scanning methodology.

Deconstructs books into structural skeletal frameworks to identify unique intellectual shifts and cognitive breakthroughs.

Transforms text and web content into high-quality visual PNGs using specialized design templates and artistic styles.

Simplifies complex academic papers into jargon-free, actionable insights using the Feynman technique and conversational analysis.

Synchronizes local Claude skills to GitHub with automatic Org-mode to Markdown conversion and documentation validation.

Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user asks to…

Generates deep, surgical, long-form articles that dissect viewpoints layer-by-layer using the Org-mode and Denote standards.

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Complete LLDB command reference — variable inspection, breakpoints, threads, expression evaluation, process control, memory commands, and…

Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory…

Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices.

Use when: (1) Entering an LLM-based Kaggle competition (open-source model required, prompt engineering, few-shot), (2) Need to choose…

Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation

Harden an LLM application against unbounded consumption with input/output caps, token budgets, rate limiting, and cost controls.