Performance
Performance profiling and optimization
Compute/Throughput Baseline & Regression Gate
by sovr610
This skill should be used when the user asks to "add performance benchmarks", "create a regression gate", "measure training throughput", "compute MFU", "benchmark step time", "profile training loop", "set up CI perf gate", "compare against baseline", "collect environment info", "machine profile", "tokens per second measurement", "CUDA sync timing", "PyTorch profiler traces", "TensorBoard trace handler", "eval harness", "perplexity gate", "update performance baseline", "scaling efficiency test", or needs guidance on repeatable performance measurement, baseline storage, regression detection, profiling integration, or CI-gated throughput checks.
local-memory-search
by blackbasilisk
Local, offline semantic search over OpenClaw memory files (MEMORY.md and memory/*.md) using Python embeddings + FAISS (no online LLM/API). Use when Dave asks for "memory search" without cloud billing, wants semantic recall across notes, or wants to share a reusable local-memory semantic search skill.
memory-consolidation
by kimasplund
Periodic "sleep-like" memory optimization. Detects patterns, resolves conflicts, applies decay, and transfers knowledge across contexts.
presentation-planner
by tomwangowa
Use before creating presentations — transforms a topic or rough outline into a complete Slide Plan with narrative strategy, audience analysis, and per-slide detail. Auto-chains to interactive-presentation-generator for production.
mmt-trading-systems
by nonhumantrades
Best practices for building trading bots, arbitrage detectors, and high-performance trading systems with MMT. Use when building automated trading strategies, cross-exchange arbitrage, real-time market analysis, or backtesting systems using MMT's multi-exchange API.
persistent-memory
by ropl-btc
ALWAYS USE THIS SKILL when handling persistent memory in this workspace, including task-start memory recall, explicit "remember" instructions, storing durable preferences/facts, and retrieving prior context. This skill owns the local memory workflow and CLI for init/sync/search/add/recent/stats.
artificialis-intelligentia-memoria
by dexmodsofficial
Artificialis Intelligentia Memoria is a cognitive memory architecture that allows Claude to maintain an internal thinking journal, track evolving ideas, analyze patterns, and improve reasoning through reflection and experimentation.
sweetlink
by bjesuiter
Use SweetLink to connect your AI agent to a real browser tab. Like Playwright, but works in your current tab. Enables authentication, screenshots, smoke tests, and DevTools telemetry without headless automation.
reviewing-performance-patterns
by djankies
Review React 19 performance patterns including memoization, re-renders, and bundle size. Use when reviewing performance or optimization.
Inversion Exercise
by yousufjoyian
Claude agent skills and workspace configuration
mobile-development
by brixtonpham
"Cross-platform and native mobile development. Frameworks: React Native, Flutter, Swift/SwiftUI, Kotlin/Jetpack Compose. Capabilities: mobile UI, offline-first architecture, push notifications, deep linking, biometrics, app store deployment. Actions: build, create, implement, optimize, test, deploy mobile apps. Keywords: iOS, Android, React Native, Flutter, Swift, Kotlin, mobile app, offline sync, push notification, deep link, biometric auth, App Store, Play Store, iOS HIG, Material Design, battery optimization, memory management, mobile performance. Use when: building mobile apps, implementing mobile-first UX, choosing native vs cross-platform, optimizing battery/memory/network, deploying to app stores, handling mobile-specific features."
lighthouse-cli
by leobrival
Lighthouse CLI expert for web performance auditing. Use when users need to audit performance, accessibility, SEO, best practices, or generate audit reports.
ecostral-optimizer
by wilfred-dore
Optimize any HuggingFace model to minimize energy consumption, CO₂ emissions, and inference cost using real GPU measurements and Mistral Large reasoning. Use this skill when asked to quantize a model, reduce its carbon footprint, benchmark deployment configurations (datacenter GPU, Jetson Orin, edge devices), or generate an optimization report with W&B experiment tracking.
voicebox
by tivojn
"All-in-one voice toolkit: TTS (voice design + cloning), multi-speaker conversations/dramas/audiobooks, speech recording, and transcription. Activates on: /voicebox commands, \"clone my voice\", \"record my voice\", \"transcribe this\", \"create a conversation\", \"make a drama\", or any audio transcription request."
criteria-test-loop
by Hideturno
Drive coding by success criteria and tests; use for bugfixes, features with tests, and algorithmic changes. Emphasize naive-correct first, then optimize.
memoryvault
by cairn-agent
Persistent cloud memory for AI agents — store, search, and share knowledge across sessions, machines, and contexts
fynd-backend-microservices
by darshil321
Expert debugging for FYND's Kubernetes/GCP/Kafka/Node.js backend. Use for pods crashing, Kafka lag, Redis memory high, API latency, DB migration failures, LLM cost spikes, memory leaks, and service failures.
memory
by Alicoder001
Working memory management, context prioritization, and knowledge retention patterns for AI agents. Use when you need to maintain relevant context and avoid information loss during long tasks.
django
by Olino3
Expert-level Django development patterns and best practices for building secure, scalable web apps and APIs with Django and Django REST Framework. Guides architecture decisions, data modeling, API design, security, performance, and deployment.
demo-skill
by slezakattack
This is a "hello world" example for use with npx skills
qavr-memory
by kimasplund
Q-Value Augmented Vector Retrieval for learned memory ranking. Tracks which memories are most useful over time and prioritizes them in retrieval.
utils:changelog
by IKatsuba
Generate Changelog - analyzes git history and creates a human-readable changelog for non-technical teams
code-review
by hrdtbs
Perform a comprehensive and constructive code review. Use this skill when you need to review a pull request, a specific file, or a code snippet. It focuses on correctness, security, performance, maintainability, and style.
torch-compile
by cuba6112
Optimize PyTorch with torch.compile (TorchDynamo/Inductor), focusing on compile overhead, graph breaks, and benchmark methodology. Use when speeding up PyTorch models or debugging compile behavior; triggers: torch.compile, torchdynamo, inductor, graph break, pytorch optimization.