Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with...
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with...
Create, update and troubleshoot AllayMC plugins in Java or other JVM languages. Use when (1) creating a new AllayMC plugin. (2) migrating an existing plugin to AllayMC. (3) troubleshooting an...
Autonomous feature development - setup and execution. Triggers on: ralph, set up ralph, run ralph, run the loop, implement tasks. Two phases: (1) Setup - chat through feature, create tasks with...
Autonomous feature development - setup and execution. Triggers on: ralph, set up ralph, run ralph, run the loop, implement tasks. Two phases: (1) Setup - chat through feature, create tasks with...
Autonomous feature development - setup and execution. Triggers on: ralph, set up ralph, run ralph, run the loop, implement tasks. Two phases: (1) Setup - chat through feature, create tasks with...
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...
Investigate a topic with Grok 4.1 via OpenRouter and generate a Markdown report with a timeline, verifiable claims, and sources (web/X). Use it when the user says “investiga…”, “haz research…”,...
Use when building web UIs with Fresh 2.x framework, using Preact components, or adding Tailwind CSS styling in Deno. Covers Fresh handlers, routes, createDefine, PageProps, context patterns,...
Generates git commit messages following Conventional Commits 1.0.0 specification with semantic types (feat, fix, etc.), optional scope, and breaking change annotations. Use when committing code...
Elite Talos Linux expert specializing in immutable Kubernetes OS, secure cluster deployment, machine configurations, talosctl CLI operations, upgrades, and production-grade security hardening....
FOLLOW THE STATE MACHINE IN SKILL.MD. When user says 'continue': (1) FIRST: Run pwd, (2) Announce STATE: CHECK_STATUS, (3) Read .claude/session.md to check Status field, (4) Route based on Status....
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...
Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via...
Generates Xiaohongshu (Little Red Book) infographic series with 9 visual styles and 6 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions...
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional...
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional...
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...