AI agent skills for performance optimization
Performance skills are valuable mainly for the discipline of measuring first. A good one refuses to suggest a change until there is a number attached to the problem, and knows the difference between a p50 and a p99 complaint. The ones to avoid hand out a list of generic optimizations — adding a cache to code that was never slow is how you get a correctness bug in exchange for nothing.
People land here searching for “claude code performance skill”, “agent skill to optimize slow code”, “web performance audit skill”.
270 performance optimization skills Refine in search →
-
omer-metin Bundle Performance HunterPerformance optimization specialist for profiling, caching, and latency optimizationUse when "performance, latency, slow query, profiling, caching, optimization, N+1, connection pool, p99, performance, profiling, caching, latency, optimization, async, database, load-testing, ml-memory" mentioned.
128 - omer-metin Bundle Performance Thinker
Performance optimization mindset - knowing when to optimize, how to measure, where bottlenecks hide, and when "fast enough" is the right answerUse when "slow, performance, optimize, profiling, benchmark, latency, throughput, cache, n+1, bottleneck, memory leak, too slow, speed up, response time, performance, optimization, profiling, caching, latency, throughput, big-o, benchmarking" mentioned.
128 -
adobe Bundle Performance TuningImprove cache efficiency, latency, and throughput for AMS deployments using the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration.
Audited 142 -
kid-sid Bundle PerformanceUse when diagnosing a slow HTTP endpoint or high-latency service — profiling, adding an application-level cache, offloading CPU-bound work to threads or workers, or defining a latency budget. For slow queries or missing indexes, use database-design or postgresql.
-
nvidia Bundle Omniverse Usd Performance TuningDiagnose and optimize slow-loading, high-memory, or low-FPS USD scenes using a structured workflow with profiling, validation, and mutation phases.
Audited 2.2k -
nguyenthienthanh Skill Perf ProfilingSystematic performance profiling and optimization across frontend (Core Web Vitals, code splitting, lazy loading), backend (N+1 queries, async), and database (EXPLAIN ANALYZE, indexing) layers. Use when the user reports slow code, latency, memory leaks, needs to benchmark, or wants to speed up an application. Measure first, optimize second. Applies Pareto principle — find the 20% of code causing 80% of slowness, fix that, not the rest.
Audited -
aeyeops Skill Optimization PatternsUse when optimizing performance, implementing caching, fixing N+1 queries, improving database queries, adding indexes, reducing latency, choosing a data structure, deciding whether to optimize at all, or reviewing code for performance anti-patterns. Covers caching strategies and the cache hierarchy, cache invalidation, the Python LRU cache and its pitfalls, N+1 detection and eager loading, index strategy, algorithmic complexity and Big-O tradeoffs, lazy loading, and connection pooling. Applies once a bottleneck is known; to find the bottleneck first, use profiling-guide.
-
github Skill Qdrant Minimize LatencyGuides optimization of Qdrant query latency by tuning segments, memory, quantization, and search parameters.
Audited 36.2k - github Skill Qdrant Search Speed Optimization
Diagnoses and resolves slow Qdrant search performance issues including high latency, low throughput, and slow filtered searches.
Audited 36.2k -
snoodleboot-io Skill Performance OptimizationThe instruction to profile before optimizing survives because intuition about
Audited 2 -
jaykim88 Skill Performance ProfilingFind and fix backend bottlenecks — connection pooling, p95/p99 latency, load testing with SLO-aligned thresholds (k6), and CPU profiling (flame graphs). Use when latency is high, throughput plateaus, or before scaling traffic. Not for DB query specifics (use query-optimization) or read-load shedding (use caching-strategy).
-
aaaaqwq Skill Performance ProfilingSystematic performance profiling and optimization methodology. Covers CPU profiling, memory profiling, heap analysis, goroutine/thread analysis, FlameGraph generation, latency profiling, database query profiling, network I/O profiling, and continuous performance regression detection. USE WHEN: investigating performance issues, optimizing slow code, reducing memory usage, diagnosing GC/CPU bottlenecks, finding N+1 queries, analyzing pprof/flamegraph output, or establishing a performance baseline. Triggers on "profiling", "performance analysis", "slow code", "flame graph", "pprof", "heap dump", "memory leak", "CPU spike", "bottleneck".
1 -
agulli Skill Performance ProfilingProfile and optimize application performance. Use when asked to improve speed, reduce latency, fix memory leaks, find bottlenecks, or optimize a slow function or endpoint.
Audited -
neuralblitz Skill Latency-----
1 -
tryboy869 Bundle Performance OptimizationApply when optimizing slow code, reducing latency, or improving throughput. Covers: profiling methodology, async optimization, database N+1, caching strategies, payload size reduction. Trigger for: slow, performance, optimize, latency, throughput, bottleneck, speed.
-
krzysztofsurdy Bundle PerformanceApplication performance optimization patterns and profiling-driven methodology. Use when the user asks to optimize application speed, reduce latency, diagnose slow queries, fix N+1 problems, implement caching layers, profile memory usage, tune database queries, apply lazy loading, configure connection pooling, or set performance budgets. Covers CPU and memory profiling, caching strategies (application, HTTP, CDN), query optimization, indexing, and load testing approaches.
Audited -
micsapp Bundle Vercel Performance TuningOptimize Vercel API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Vercel integrations. Trigger with phrases like "vercel performance", "optimize vercel", "vercel latency", "vercel caching", "vercel slow", "vercel batch".
3 -
kreek Bundle PerformanceUse for performance, profiling, latency, throughput, allocation, caching, hot paths.
Audited -
stifleur390 Skill Laravel PerformanceOptimisation des performances Laravel 13. Cache, query optimization, profiling, lazy loading, Pulse. Utiliser quand on optimise une app lente, on debug des requêtes lentes, on configure le cache, ou on profile.
-
softspark Skill Performance ProfilingPerformance: golden signals, p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, memory leak.
- micsapp Bundle Supabase Performance Tuning
Optimize Supabase API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Supabase integrations. Trigger with phrases like "supabase performance", "optimize supabase", "supabase latency", "supabase caching", "supabase slow", "supabase batch".
3 -
htlin222 Skill PerfProfile and optimize bottlenecks. Use for performance issues or caching strategies.
-
roanbrasil Skill Performance ProfilingInvoked when the user needs to profile, benchmark, or optimize performance of a Java/JVM, Python, or Rust application — including CPU, memory, I/O, GC, or async bottlenecks.
-
ashutoshsrivastava17 Skill Performance ProfilingAnalyze application performance bottlenecks — CPU, memory, I/O, query time, rendering. Produce optimization recommendations with expected impact. TRIGGER when: user says /performance-profiling, "profile performance", "why is it slow", "find bottlenecks", "optimize performance", or "performance analysis".
Audited
How to install a performance optimization skill
- Compare the skills. Read the performance optimization skills below — each page shows the full SKILL.md, its safety verdict, and the capabilities it declares.
- Install it. Run npx skillmds@latest add <owner>/<name>. The CLI writes the skill into every agent directory it detects, or use --agent to pin one.
- Use it. Restart your agent. It loads the skill on demand the next time you ask for something that matches — you do not have to name the skill.
What makes a good performance optimization skill?
Performance skills are valuable mainly for the discipline of measuring first. A good one refuses to suggest a change until there is a number attached to the problem, and knows the difference between a p50 and a p99 complaint. The ones to avoid hand out a list of generic optimizations — adding a cache to code that was never slow is how you get a correctness bug in exchange for nothing.
Every skill listed here is a plain SKILL.md file in the format Anthropic documents for Agent Skills, read unchanged by Cursor, OpenAI Codex and 60+ agents. Each passes a safety review before it is publicly listed; the verdict and declared capabilities are on every skill's page.
Frequently asked questions
What is an agent skill for performance optimization?
Performance skills are valuable mainly for the discipline of measuring first. A good one refuses to suggest a change until there is a number attached to the problem, and knows the difference between a p50 and a p99 complaint. The ones to avoid hand out a list of generic optimizations — adding a cache to code that was never slow is how you get a correctness bug in exchange for nothing.
Can a performance skill profile my app?
It can tell the agent which profiler to run and how to read the output, but the measurement happens through tools you already have. Skills that only reason about code without a measurement step are best treated as review checklists.
Which agents can use these performance optimization skills?
Any agent that reads SKILL.md files: Claude Code, Claude.ai, Cursor, OpenAI Codex, Windsurf, OpenCode and 60+ others. The format is not vendor-specific, so the same file works everywhere — each agent just keeps its skills in a different directory, listed at /agents.
Are these performance optimization skills free?
Yes. Searching, reading and installing skills on SkillMD is free and needs no account. Individual skills carry their own licence, shown on each skill's page.