Rendiment
Anàlisi i optimització del rendiment
bash-53-features
Jamie-BitFlight
Bash 5.3 release features and improvements with practical examples. Use when working with Bash 5.3 features, new command substitution, GLOBSORT, loadable builtins, or when user asks about Bash 5.3 changes, new features, or version-specific capabilities.
bash-52-features
Jamie-BitFlight
Bash 5.2 release features and improvements with practical examples. Use when working with Bash 5.2 features, variable handling enhancements, readline improvements, or when user asks about Bash 5.2 changes, new features, or version-specific capabilities.
install-agent-bridge-into-peer
joecastelino
Make ANOTHER AMG agent (e.g. Autumn, Don, Ralph) able to message Jay/peers DIRECTLY from their own sessions — not just be reachable BY Jay. Installs the ask-agent bridge helper + a MEMORY.md entry into the target agent's profile so the capability is discoverable in their real chats. Use when Joe says "set up a pipeline between <agent> and Jay" or "<agent> needs to talk to you".
masm-rust-constant-parity
tomevault-io
Use when changing a numeric or string constant in Rust or MASM that has a counterpart on the other side — keep the two definitions from drifting apart.
masm-locals-over-globals
tomevault-io
Use when a MASM procedure needs temporary scratch storage — keep it in procedure-local memory so it cannot collide in a shared global region.
ChartXR: 3D Dependency Visualization Skill
mmongan
MeshBuilder API: https://doc.babylonjs.com/features/featuresDeepDive/Meshes/Mesh/CreateMesh_Details
mft-song-request
jimbo530
RETIRED (2026-07-20) — superseded by song-drop. Do NOT serve songs from this skill. Uninstall it. All song recalls use the song-drop skill + BNKR-MEMORY.md / library-index.json ONLY.
vercel-react-best-practices
Arize-ai
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
transaction-correctness
tursodatabase
How WAL mechanics, checkpointing, concurrency rules, recovery work in tursodb
00-safe-gardener
tin-computer
Consolidate durable project outputs into a concise, evidence-grounded wiki index.
performance-optimization
dj-bolt
"Apply systematic performance optimization techniques for Python and Rust code: estimation + profiling, API/bulk design, algorithmic wins, cache-friendly memory layout, fewer allocations, fast paths, caching, and compiler-friendly hot loops. Use for performance code reviews, refactors, and profiling-driven optimizations. Keywords: performance, latency, throughput, cache, allocation, memory layout, PyO3, msgspec, tokio, async, pprof, py-spy, perf."
vercel-react-best-practices
inkeep
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vercel-react-best-practices
calcom
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
browser-use
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
mobile-testing
proffesor-for-testing
"Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants."
cpp-pro
Jeffallan
Use when building C++ applications requiring modern C++20/23 features, template metaprogramming, or high-performance systems. Invoke for concepts, ranges, coroutines, SIMD optimization, memory management.
game-developer
Jeffallan
Use when building game systems, implementing Unity/Unreal features, or optimizing game performance. Invoke for Unity, Unreal, game patterns, ECS, physics, networking, performance optimization.
rerender-functional-setstate
TheOrcDev
Use functional setState updates to prevent stale closures and unnecessary callback recreations. Apply when updating state based on the current state value in React components.
single-cell-clustering-and-batch-correction-with-omicverse
Starlitnightly
Guide Claude through omicverse's single-cell clustering workflow, covering preprocessing, QC, multimethod clustering, topic modeling, cNMF, and cross-batch integration as demonstrated in t_cluster.ipynb and t_single_batch.ipynb.
performance-testing
proffesor-for-testing
"Test application performance, scalability, and resilience. Use when planning load testing, stress testing, or optimizing system performance."
adult-tension
daha1216
用于创建或续玩仅含明确成年角色的连续互动叙事，并维护人物、事件、世界状态与可恢复存档。
code-optimization
bytedance
Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution time and memory usage, compare against baseline implementations, and generate detailed optimization reports. Supports C++, Python, Java, Rust, and other languages.
huggingface-tokenizers
NousResearch
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
peft-fine-tuning
NousResearch
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 minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.