Performance
Performance profiling and optimization
perf-code-paths
by ComposioHQ
"Use when mapping code paths, entrypoints, and likely hot files before profiling."
note
by Yeachan-Heo
Save notes to notepad.md for compaction resilience
learn-about-omx
by Yeachan-Heo
Learn about your OMX usage patterns and get personalized recommendations
training-llms-megatron
by davila7
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
model-selection
by majiayu000
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.
react-native-best-practices
by callstackincubator
Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead, FlashList, native modules, or debugging jank and frame drops.
godot-audio-systems
by thedivergentai
"Expert patterns for Godot audio including AudioStreamPlayer variants (2D positional, 3D spatial), AudioBus mixing architecture, dynamic effects (reverb, EQ,compression), audio pooling for performance, music transitions (crossfade, bpm-sync), and procedural audio generation. Use for music systems, sound effects, spatial audio, or audio-reactive gameplay. Trigger keywords: AudioStreamPlayer, AudioStreamPlayer2D, AudioStreamPlayer3D, AudioBus, AudioServer, AudioEffect, music_crossfade, audio_pool, positional_audio, reverb, bus_volume."
game-hacking-techniques
by gmh5225
Guide for game hacking techniques and cheat development. Use this skill when researching memory manipulation, code injection, ESP/aimbot development, overlay rendering, or game exploitation methodologies.
dma-attack-techniques
by gmh5225
Guide for Direct Memory Access (DMA) attack techniques using FPGA hardware. Use this skill when researching PCIe DMA attacks, pcileech, FPGA firmware development, or hardware-based memory access for game security research.
windows-kernel-security
by gmh5225
Guide for Windows kernel security research including driver development, system callbacks, security features, and kernel exploitation. Use this skill when working with Windows drivers, PatchGuard, DSE, or kernel-level security mechanisms.
serving-llms-vllm
by davila7
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
context-window-management
by davila7
"Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context."
agent-memory-mcp
by davila7
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
reflexion:memorize
by NeoLabHQ
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
ai-agents-architect
by davila7
"Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling."
llama-cpp
by davila7
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 (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
unsloth
by davila7
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
godot-3d-lighting
by thedivergentai
"Expert patterns for Godot 3D lighting including DirectionalLight3D shadow cascades, OmniLight3D attenuation, SpotLight3D projectors, VoxelGI vs SDFGI, and LightmapGI baking. Use when implementing realistic 3D lighting, shadow optimization, global illumination, or light probes. Trigger keywords: DirectionalLight3D, OmniLight3D, SpotLight3D, shadow_enabled, directional_shadow_mode, directional_shadow_split, omni_range, omni_attenuation, spot_range, spot_angle, VoxelGI, SDFGI, LightmapGI, ReflectionProbe, Environment, WorldEnvironment."
Executive Resume Writer
by Paramchoudhary
Create C-suite and VP level resumes emphasizing strategic leadership
perf-profiler
by ComposioHQ
"Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence."
godot-characterbody-2d
by thedivergentai
"Expert patterns for CharacterBody2D including platformer movement (coyote time, jump buffering, variable jump height), top-down movement (8-way, tank controls), collision handling, one-way platforms, and state machines. Use for player characters, NPCs, or enemies. Trigger keywords: CharacterBody2D, move_and_slide, is_on_floor, coyote_time, jump_buffer, velocity, get_slide_collision, one_way_platforms, state_machine."
godot-adapt-single-to-multiplayer
by thedivergentai
"Expert patterns for adding multiplayer to single-player games including client-server architecture, authoritative server design, MultiplayerSynchronizer, lag compensation (client prediction, server reconciliation), input buffering, and anti-cheat measures. Use when retrofitting multiplayer, porting to online play, or designing networked gameplay. Trigger keywords: MultiplayerPeer, ENetMultiplayerPeer, SceneMultiplayer, MultiplayerSynchronizer, rpc, rpc_id, multiplayer_authority, client_prediction, server_reconciliation, lag_compensation, rollback."
videocut:高清化
by Ceeon
视频高清导出。2-pass编码+锐化，匹配或超越原片画质。触发词：高清化、高清导出、导出高清、渲染高清
context-degradation
by guanyang
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.