性能
性能分析与优化
cpu-gpu-performance
athola
'Use this skill BEFORE resource-intensive operations. Establish baselines
skills-eval
athola
Evaluate and improve Claude skill quality through auditing. Use when
performance-optimization
Hack23
Application performance tuning, JVM optimization, database query tuning, Vaadin UI performance
maven-build-management
Hack23
Manage multi-module Maven builds: dependencies, plugins, profiles, reproducible builds
slack-memory-store
krafton-ai
Comprehensive memory storage system for AI employees in IT companies who communicate via Slack. Automatically classifies and stores diverse information types (Slack messages, Confluence docs, emails, meetings, projects, decisions, feedback) in an organized folder structure with efficient indexing and retrieval. Use when managing or searching employee memory, storing conversations, documenting decisions, tracking projects, or organizing any work-related information.
slack-memory-retrieval
krafton-ai
Retrieve and utilize stored memories for AI employees in Slack environments. Efficiently searches and loads relevant context (channels, users, projects, decisions, meetings) from organized memory storage to inform responses. Use this when answering questions that require historical context, user preferences, project status, or any previously stored information. Works with slack-memory-store storage system.
slack-memory-cleanup
krafton-ai
Memory cleanup and organization skill for AI employees. Provides guidelines for detecting duplicates, fixing misclassified files, and removing stale information from memory storage.
organizational-design
RefoundAI
Help users design effective organizational structures. Use when someone is thinking about team structure, deciding between functional vs. divisional models, planning a reorg, or figuring out how to structure product teams.
nav-features
alekspetrov
Show and toggle Navigator features. Auto-invoke when user says "show features", "enable/disable feature", "my navigator settings", or "configure navigator".
nav-graph
alekspetrov
Query project knowledge graph. Search across tasks, SOPs, memories, and concepts. Use when user asks "what do we know about X?", "show everything related to X", or "remember this pattern/pitfall/decision".
game-servers
pluginagentmarketplace
Game server architecture, scalability, matchmaking, and backend systems for online games. Build robust, scalable multiplayer infrastructure.
add-memory
openakita
Record important information to long-term memory for learning user preferences, successful patterns, and error lessons. When you need to remember user preferences, save successful patterns, or record lessons from errors.
verify
pubkey
Verifies code changes by running tests and generation scripts
tilelang-developer
yzlnew
"Write, optimize, and debug high-performance AI compute kernels using TileLang (a Python DSL for GPU programming). Use when the user requests: (1) Writing custom GPU kernels for AI workloads (GEMM, Attention, MLA, etc.), (2) Optimizing existing TileLang code for NVIDIA, AMD, or Ascend hardware, (3) Implementing non-standard operators (like DeepSeek MLA, FlashAttention variants), (4) Debugging TileLang compilation or runtime errors, or (5) Cross-platform kernel development targeting multiple GPU vendors."
megatron-memory-estimator
yzlnew
Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models. Use when users need to (1) estimate memory from HuggingFace model configs (DeepSeek-V3, Qwen, etc.), (2) plan GPU resource allocation for training, (3) compare different parallelism strategies (TP/PP/EP/CP), (4) determine if a model fits in available GPU memory, or (5) optimize training configurations for memory efficiency.
mz-profile
MaterializeInc
This skill should be used when the user wants to "profile Materialize", "check memory usage", "analyze binary size", "debug performance", or mentions profiling, samply, heaptrack, flame graphs, memory checking, binary size analysis, slow queries, or high CPU/memory usage in the Materialize repository. Use this skill even if the user just says something is "slow" or "using too much memory" without explicitly mentioning profiling.
stacks-feature-flags
stacksjs
Use when implementing per-user or per-team feature rollouts, persisted flag values, percentage experiments, or weighted variants. Covers @stacksjs/feature-flags and config/feature-flags.ts.
vvvv-troubleshooting
tebjan
Diagnoses and fixes common vvvv gamma errors in C# nodes, SDSL shaders, and runtime behavior. Use when encountering errors, exceptions, crashes, red nodes, shader compilation failures, missing nodes in the browser, performance issues, or unexpected behavior.
vvvv-fundamentals
tebjan
Explains vvvv gamma core concepts — data types, frame-based execution model, pins, pads, links, node browser, live compilation (source project vs binary reference workflows), .vl document structure, file types (.vl/.sdsl/.cs/.csproj), ecosystem overview, and AppHost runtime detection. Use when the user asks about vvvv basics, how vvvv works, the live reload model, when to patch vs code, or needs an overview of the visual programming environment.
caching-strategy-helper
proflead
Recommend caching strategies and invalidation patterns. Use when a mid-level developer needs performance guidance.
performance-budgeting
proflead
Define performance budgets and guardrails. Use when a senior developer needs performance targets and enforcement.
data-structure-chooser
proflead
Recommend basic data structures for a task. Use when a junior developer needs help choosing lists, maps, or sets.
hipocampo-protocol
carrasquelalex1
Protocolo de memoria dual con Sparse Selective Caching (SSC). Persiste en memoria_vectorial y memory_items con búsqueda semántica progresiva.
session-memory
romiluz13
"Internal skill. Use cc10x-router for all development tasks."