codex-self-rewriting
Lisp machine self-modification patterns via MCP Tasks and Narya bridge
Lisp machine self-modification patterns via MCP Tasks and Narya bridge
UV/UVX/Ruff toolchain for DiscoHy Thread Operad with Python packaging and linting
Guides users through migrating to Rust 2024 edition features including let chains, async closures, and improved match ergonomics. Activates when users work with Rust 2024 features or nested control flow.
Interface nil trap - typed nil is not nil
WebGPU tile rendering for Rio Terminal via wgpu and sugarloaf. Extends
ASI skill integrating polynomial functors, free monad/cofree comonad
oapply: Operad algebra evaluation via colimits. Composes machines/resource sharers.
RAN energy efficiency optimization with cognitive consciousness, predictive power management, and autonomous energy-saving strategies for sustainable network operations. Use when optimizing RAN energy consumption, implementing green network strategies, reducing operational costs, or enabling energy-efficient 5G networks.
Self-inverse derivation patterns where ι∘ι = id for frame-invariant self
DisCoPy categorical color streams via Hy with 3 parallel TAP streams and 7 operad variants
Paperback-compatible extension runtime and source API
Self-inverse derivation patterns where ι∘ι = id for frame-invariant self
Invoke SYNTHESIZER Deputy for operations, execution, and cross-domain coordination.
Universal Python development guidelines and best practices
An example skill demonstrating the format for opencode-skills plugin
Production-grade skill for modern C++ development with C++11 through C++23 features. Covers move semantics, smart pointers, lambdas, concepts, ranges, coroutines, and modules.
Create and execute advanced execution plans for complex AI model development incorporating 2024-2026 cutting-edge techniques (DeepSeek GRPO, manifold-constrained architectures, geometric scaling). Use when planning large-scale model training, architecture optimization, or multi-stage development workflows requiring state-of-the-art methodologies.
Expert in Apache Ray distributed computing. Use when converting Python code to Ray workloads, debugging Ray applications, optimizing Ray performance, or working with Ray Core, Ray Data, Ray Train, Ray Serve, or Ray Tune. Automatically fetches relevant documentation from Ray, HuggingFace, PyTorch, and other ML/distributed frameworks based on code context.
Execute GGUF quantization with imatrix protection, perform statistical benchmark evaluation with error bars, generate academic-style methodology documentation, and create comprehensive scorecards. Use when evaluating model quantization quality, comparing quantization methods, or generating publication-ready evaluation results with subagent execution and PowerShell progress visualization.
This skill should be used when the user asks about "Burn tensors", "tensor operations", "Module derive", "burn config", "autodiff", "backward pass", "gradient", "record serialization", "model weights", or core Burn application development patterns.
Cirrus Logic MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Cirrus Logic audio ICs, Wolfson audio products, or CirrusLogicHandler.
Achieve and maintain low input latency by engineering event-to-render pipelines.