SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
agent-device
Controls and inspects iOS, tvOS, macOS and Android apps for agents: snapshots, UI interactions (tap/type/scroll), logs, network and perf capture.
skills
Guides using Bun — a fast all-in-one JavaScript runtime, bundler, package manager and test runner — to speed Node.js projects, bundle TypeScript, run tests, and
opencode-skills-collection
Profile, analyze, and optimize Python applications for CPU and memory efficiency using profiling tools and performance best practices.
skill
Provides Bun runtime and package manager patterns for fast local JS/TS development, with examples for running scripts and installing dependencies.
specialist-agent
Audit landing pages and user flows to find conversion friction and deliver prioritized, testable A/B recommendations.
smart-blog-skills
Integrates PageSpeed Insights and Chrome UX Report (CrUX) to provide PageSpeed and Core Web Vitals analysis for blog posts, with optional API key setup and conf
aberdeen
Guidance for AI assistants and developers on building fine-grained reactive UIs with the Aberdeen library—patterns for proxies, efficient list rendering, transi
megatron-bridge
Guides enabling and validating MoE expert-parallel communication overlap in Megatron-Bridge to hide dispatch/combine latency and improve throughput.
axiom
Comprehensive routing and diagnostics for app performance problems: memory leaks, CPU bottlenecks, app launch, hangs, and battery/energy issues with actionable
claude-skill-registry
Guidance and patterns for Python parallelism and GPU/CPU performance: threading vs multiprocessing vs asyncio, CUDA streams, PyTorch DDP, and benchmarking.
ostack-saas
Automated performance benchmarking and regression detection: captures baselines, measures Core Web Vitals, and compares metrics across PRs to flag regressions.
animations
A Svelte 5 port of Motion (Framer Motion) providing animation components, gesture props and layout helpers for smooth UI transitions.
claude-spellbook
Structured, end-to-end guidance for designing scalable, reliable systems: requirements, capacity estimation, architecture, and failure-mode planning.
zorai
Conducts deep performance audits across databases, memory, algorithms, concurrency, I/O, bundling, and more using specialist agents and pattern-based detection.
std
An arena-first C++ design philosophy: use a single ObjPool to own related objects, favour interface pointers, and prefer pool-allocated containers for predictab
awesome-omni-skill
Diagnose application performance bottlenecks and design optimizations across backend, database, caching and frontend Core Web Vitals.
tao
Structured performance-audit methodology: measure, identify bottlenecks, optimize the true hotspot, and verify improvements with benchmarks.
ai-toolkit
Guidelines and patterns for implementing prompt caching with Anthropic APIs to reduce input-token costs and latency, including TTLs, breakpoints, and hit-rate m
skills
Guidance and configs to enable expert-parallel communication overlap in Megatron-Bridge for MoE models — use to hide dispatch/combine latency and improve throug
codescalebench
Launch, manage, and rerun CodeScaleBench benchmark suites with safety guardrails, paired baseline+full execution, and orchestration utilities.
agentup
A comprehensive Go development assistant that generates architectures, patterns, project scaffolds, and best-practice guidance for web, CLI, microservice and da
gstack
Measure and detect performance regressions for web pages using automated benchmarks, baselines, and trend analysis.
skillshub
Lighthouse-led web performance audits and actionable optimizations to reduce load time, improve Core Web Vitals, and cut total page weight.
data-engineering-skills
Expert guidance for deploying, configuring, and developing with Apache Iggy — a Rust-native high-performance message streaming platform, including Docker, Pytho
