SWE Performance Hunt
技能 已验证 活跃Hunts for concrete performance bottlenecks in a scoped repository surface using profiler output, benchmarks, query plans, traces, bundle analysis, or repo evidence, then returns the smallest high-value follow-up experiments or fixes. Use when a user says `find performance bottlenecks`, `why is this slow`, `profile this flow`, `hunt hot paths`, or asks for a recurring performance review. Do NOT use for live incident response, generic observability audits, speculative micro-optimization, or broad architecture rewrites with no bottleneck evidence.
To help users find concrete performance bottlenecks in their codebases and generate a ranked list of actionable, low-risk follow-up experiments or fixes.
功能
- Hunts for performance bottlenecks in scoped repositories
- Analyzes profiler output, benchmarks, traces, and query plans
- Identifies high-value follow-up experiments or fixes
- Distinguishes measured bottlenecks from weak suspicions
- Ranks findings by user and system impact
使用场景
- Find performance bottlenecks in a service, job, page, or query path
- Understand why a specific flow is slow
- Audit recent performance regressions with concrete evidence
- Rank hot paths before starting optimization work
非目标
- Live incident response or active outage triage
- Generic observability coverage audits
- Speculative micro-optimization with no measured impact
- Broad architecture rewrites without bottleneck evidence
工作流
- Define the performance surface (scope, metric)
- Gather the strongest evidence first (profiler, benchmarks, traces)
- Map the critical path (entry points, loops, boundaries)
- Separate bottlenecks from suspicion (strong, moderate, weak evidence)
- Rank by user and system impact
- Propose minimal follow-up work (surface, evidence, cause, next step, validation)
- Call out unknowns (missing data, inferred findings)
安装
/plugin install swe-skills@ckorhonen-swe-skills质量评分
已验证类似扩展
Benchmark
100Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". (gstack) Voice triggers (speech-to-text aliases): "speed test", "check performance".
Performance Analysis
100Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
MongoDB Connection Optimizer
100为任何支持的驱动程序语言优化 MongoDB 客户端连接配置（池、超时、模式）。在处理/更新/审查实例化或配置 MongoDB 客户端（例如，调用 `connect()` 时）、配置连接池、对连接错误（ECONNREFUSED、超时、池耗尽）进行故障排除、优化与连接相关的性能问题时，请使用此技能。这包括构建具有 MongoDB 的无服务器函数、创建使用 MongoDB 的 API 端点、优化高流量 MongoDB 应用程序、创建长期运行任务和并发性，或调试与连接相关的失败等场景。
Sql Optimization
100Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Provides execution plan analysis, pagination optimization, batch operations, and performance monitoring guidance.
Core Web Vitals
100优化核心 Web 指标（LCP、INP、CLS），以获得更好的页面体验和搜索排名。当被要求“改进核心 Web 指标”、“修复 LCP”、“减少 CLS”、“优化 INP”、“页面体验优化”或“修复布局偏移”时使用。
V3 Performance Engineer
99Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer