AI Agent Skills

Performance review checklist — hot paths, async-runtime discipline, streaming, query-client tuning, layout pre-measurement, token/cost. Load when reviewing perf-sensitiv…

Use when mapping code paths, entrypoints, and likely hot files before profiling.

基于可复现基线和 profiler 证据分析性能问题。用于用户要求定位慢接口、慢任务、慢查询、内存或网络瓶颈，制定优化方案，或验证优化收益时；区分实测结论与静态推断，不虚构耗时和提升比例，生产环境操作需明确授权。

Three.js 性能优化指南。当 Three.js/React Three Fiber 项目出现掉帧、内存增长、加载缓慢、绘制调用过多，或需要迁移 WebGPU、实现大规模粒子/实例化渲染、配置资源压缩管线时使用。触发关键词："Three.js 优化"、"WebGPU"、"draw calls"、"内存泄漏"、"TSL"、"Insta…

React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

Measure portfolio returns, risk, drawdowns, benchmarks, rolling metrics, and strategy performance from approved data.

Perform a forensic company financial-statement review across earnings quality, health, fraud risk, and operating efficiency.

Turn creator performance data into a documented retrospective, grounded hypotheses, and reusable content learnings.

Golang skills orchestrator — always active on any Golang coding, review, debug, or setup task. Reads the task context and loads the most relevant skills from samber/cc-s…

Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memo…

Reviews React Native TV apps for focus/D-pad navigation, 10-foot UI layout, TV playback/DRM integration, low-memory TV performance, and TV accessibility. Use when buildi…

Guided journey from a live website that underperforms to a prioritized, evidence-backed backlog of conversion, usability, message, and speed fixes - each shipped as a te…

Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benc…

Build, debug, or review WebGPU renderer work — three.js/TSL scene layers, node materials, or raw WGSL passes and compute. Use when changing GPU resource layouts, render…

Use when writing production-grade GDScript — performance idioms, metaprogramming, @tool lifecycle, async pitfalls, signal/Callable trade-offs, profiler-driven idioms, an…

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.