> browse/registry

> eval-driven-dev

Add instrumentation, build golden datasets, write eval-based tests, run them, root-cause failures, and iterate — Ensure your Python LLM application works correctly. Make sure to use this skill whenever a user is developing, testing, QA-ing, evaluating, or benchmarking a Python project that calls an LLM. Use for making sure an LLM application works correctly, catching regressions after prompt changes, fixing unexpected behavior, or validating output quality before shipping.

> astro

Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.

> k6-load-testing

Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.

> claude-monitor

Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.

> agent-evaluation

You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer.

> run-rust-benchmarks

Run Rust benchmarks and compare performance with the C implementation. Use this when you work on migrating C code to Rust and want to ensure performance is not regressed.

> skill-creator-pro

Create new skills, modify and improve existing skills, and measure skill performance. Enhanced version with quick commands. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. Triggers on phrases like "make a skill", "create a new skill", "build a skill for", "improve this skill", "optimize my skill", "test my skill

> swift-optimise

Swift 6.2 and SwiftUI performance optimization for iOS 26 clinic architecture codebases. Covers async/await concurrency patterns, Sendable/actor isolation, view/render performance, and animation performance while preserving modular MVVM-C boundaries across App, Feature, Domain, and Data layers. Use when profiling or optimizing Swift/SwiftUI behavior in clinic modules.

> rust-optimise

Rust performance optimization covering memory allocation, ownership efficiency, data structure selection, iterator patterns, async concurrency, algorithm complexity, compile-time optimization, and micro-optimizations. Use when optimizing Rust code performance, profiling hot paths, reducing allocations, or choosing optimal data structures. Complements the rust-refactor skill (idiomatic patterns and architecture). Does NOT cover code style, naming conventions, or project organization (see rust-ref

> ios-xcode

Xcode setup and tooling guidance for iOS 26 / Swift 6.2 clinic modular MVVM-C projects covering project configuration, SwiftData container wiring, testing, debugging, profiling, and distribution workflows. Use when configuring App-target infrastructure or day-to-day tooling around clinic architecture modules.

> react-optimise

Application-level React performance optimization covering React Compiler mastery, bundle optimization, rendering performance, data fetching, Core Web Vitals, state subscriptions, profiling, and memory management. Use when optimizing React app performance, analyzing bundle size, improving Core Web Vitals, or profiling render bottlenecks. Complements the react skill (API-level patterns) with holistic performance strategies. Does NOT cover React 19 API usage (see react skill) or Next.js-specific fe

> ue-testing-debugging

Use when writing automation tests, functional tests, or any test in Unreal Engine. Also use when the user asks about "UE_LOG", logging, log categories, assertion, check, ensure, verify, DrawDebug, debug draw, console command, profiling, Unreal Insights, stat commands, or debugging techniques. See ue-module-build-system for test module setup, and ue-cpp-foundations for general C++ logging patterns.

> go-performance

Use when optimizing Go code, investigating slow performance, or writing performance-critical sections. Also use when a user mentions slow Go code, string concatenation in loops, or asks about benchmarking, even if the user doesn't explicitly mention performance patterns. Does not cover concurrent performance patterns (see go-concurrency).

> go-testing

Use when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff. Also use when a user asks to write a test for a Go function, even if they don't mention specific patterns like table-driven tests or subtests. Does not cover benchmark performance testing (see go-performance).

> ue-benchmark

UE Agent Benchmark 评测框架。定义通用评分体系、评测流程和质量层级，支持多场景 Benchmark。触发：用户提及 Benchmark/评测/基准测试/跑分 等关键词时激活。

> wp-performance-backend

WordPress backend performance optimization — profiling, queries, object cache, autoload, cron, and remote HTTP. Always-active rules when investigating slowness issues.

> oss-code-analysis

Explore open-source GitHub repository source trees via web browsing to analyze and compare feature implementations at the code level. Supports two modes: cross-project comparison and single-project deep dive. Use when evaluating how OSS projects implement a specific feature, choosing architecture patterns, or benchmarking implementation strategies.

> competitive-feature-benchmark

Research and compare how competing products implement a similar feature at the UX and interaction level. Provides structured comparison tables and strategic differentiation recommendations.

> nginx

Use this skill when helping with Nginx or OpenResty/Lua development tasks. Triggers include writing or debugging Nginx configuration (server blocks, location blocks, upstreams, proxy_pass, rewrites, maps, try_files), OpenResty/Lua module development (content handlers, access control, header manipulation, shared dictionaries, cosocket usage), and Nginx performance tuning (buffer sizing, keepalive tuning, caching, connection pooling, benchmarking). Also use when the user mentions .conf files, ngin

> capacity-planner

Translates performance test results into infrastructure scaling recommendations with cost estimates. Use when someone has load test data and needs to know what infrastructure changes are required to handle target traffic. Trigger words: capacity planning, scaling plan, infrastructure sizing, how many pods, RDS sizing, handle more traffic, scale for launch.