GitHub
vram-gpu-oom
GPU VRAM management patterns for sharing memory across services (Ollama, Whisper, ComfyUI). OOM retry logic, auto-unload on idle, and service signaling protocol.
☆ 6View skill
tools framework internals AI Skills
Discover tools framework internals skills, compare source repositories and read the instructions for each workflow.
Categories: tools framework internals
tools framework internals Clear filters
Browse skills
GitHub
attribution-patching
Gradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or when analyzing many components simultaneously.
☆ 6View skill
GitHub
mlx-dev
Write correct, idiomatic Apple MLX code for Apple Silicon ML. Use when working with MLX arrays, neural networks, training loops, lazy evaluation, unified memory, mx.eval, mx.compile, Metal GPU, memory optimizat...
☆ 6View skill
GitHub
godot-optimization
Expert knowledge of Godot performance optimization, profiling, bottleneck identification, and optimization techniques. Use when helping improve game performance or analyzing performance issues.
☆ 6View skill
GitHub
line-cook
AI-supervised development workflow. Use when running prep, cook, serve, tidy, or work commands, managing beads issues during sessions, or following prep→cook→serve→tidy cycle. Covers workflow orchestration, gua...
☆ 6View skill
GitHub
pythonmodern-python
Modern Python language features and typing patterns. Use when writing type hints, using generics, implementing pattern matching, working with async/await, or leveraging Python 3.10+ features.
☆ 6View skill
GitHub
greycat-c
GreyCat C API and GCL Standard Library reference. Use for: (1) Native C development with gc_machine_t context, tensors, objects, memory management, HTTP, crypto, I/O; (2) GCL Standard Library modules - std::cor...
☆ 5View skill
GitHub
uv-discohy
UV/UVX/Ruff toolchain for DiscoHy Thread Operad with Python packaging and linting
☆ 5View skill
GitHub
enzyme-autodiff
Enzyme.jl Automatic Differentiation Skill
☆ 5View skill
GitHub
hvm-runtime
HVM Runtime Skill
☆ 5View skill
GitHub
discopy-operads
DiscoPy Operads Skill
☆ 5View skill
GitHub
discohy-streams
DisCoPy categorical color streams via Hy with 3 parallel TAP streams and 7 operad variants
☆ 5View skill
GitHub
oapply-colimit
oapply: Operad algebra evaluation via colimits. Composes machines/resource sharers.
☆ 5View skill
GitHub
rio-webgpu-tiles
WebGPU tile rendering for Rio Terminal via wgpu and sugarloaf. Extends
☆ 5View skill
GitHub
reverse-engineering
Reverse Engineering Skill
☆ 5View skill
GitHub
mlx-jax-splitmix
MLX on Apple Silicon with JAX-style SplitMix64 PRNG. Deterministic color generation with GPU acceleration.
☆ 5View skill
GitHub
homoiconic-rewriting
Unified homoiconic graph rewriting - λ-calculus, interaction nets, ACSets, CUDA parallelism
☆ 5View skill
GitHub
specter-navigator-gadget
Unified Specter/Navigator/3-MATCH architecture with bidirectional path compilation
☆ 5View skill
GitHub
fuzzing-obstacles
Overcoming fuzzing obstacles and improving fuzzer effectiveness.
☆ 5View skill
GitHub
specter-acset
Specter-style bidirectional navigation for Julia Collections, S-expressions, and ACSets with inline caching
☆ 5View skill
GitHub
unworlding-involution
Self-inverse derivation patterns where ι∘ι = id for frame-invariant self
☆ 5View skill
GitHub
cat
cat Skill: Derivational Pipe Chaining
☆ 5View skill
GitHub
asi-polynomial-operads
ASI skill integrating polynomial functors, free monad/cofree comonad
☆ 5View skill
GitHub
uv-discohy
UV/UVX/Ruff toolchain for DiscoHy Thread Operad with Python packaging and linting
☆ 5View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.