AI Agent Skills

Concept Bottleneck Models, ICML 2020

Serenity-inspired Agent Skill for supply-chain bottleneck stock research

Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, wh…

Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent exe…

Golang performance optimization patterns and methodology - if X bottleneck, then apply Y. Covers allocation reduction, CPU efficiency, memory layout, GC tuning, pooling,…

Serenity-style "Chokepoint Theory" applied to AI supply chains. Identifies physically irreplaceable bottleneck suppliers — small-cap near-monopolies buried 4–7 layers de…

Debug and optimize Android/Gradle build performance. Use when builds are slow, investigating CI/CD performance, analyzing build scans, or identifying compilation bottlen…

Optimizes a measured latency, throughput, memory, CPU, or I/O problem through profiling and keep-or-discard experiments. Use for a known bottleneck; not unbiased A/B com…

Compares tools or implementations through reproducible A/B workloads, correctness oracles, and controlled measurements. Use to choose alternatives; not to optimize a kno…

Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks

Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process i…

Load tests API endpoints with progressive concurrency. Measures response times, error rates, throughput, and identifies breaking points. Generates a detailed report with…

Supply chain mapping, supplier dependency analysis, customer concentration, geographic concentration, bottleneck identification, supply chain risk, logistics network, so…

Design and implement end-to-end client onboarding workflows from prospect intake through funded account, covering KYC verification, document collection, e-signature, and…

Comprehensive guide and toolkit for diagnosing Rspack build issues. Quickly identify where crashes/errors occur, or perform detailed performance profiling to resolve bot…

Pre-implementation red-team analysis. Use when a plan is high-risk, critical path, or expensive to reverse. Challenges plans before code is written — finds edge cases, s…