Loading...
Loading...
Found 2,256 Skills
React rendering performance patterns. Use when reducing re-renders, optimizing memoization, state design, or reviewing React performance.
Analyze previous Jetty workflow runs and propose targeted improvements to your runbook. Use when the user wants to optimize, improve, or debug a runbook based on past execution results — including 'optimize runbook', 'improve runbook', 'why is my runbook failing', 'analyze my runs', 'runbook not working well', 'make my runbook better', 'debug runbook performance', or 'learn from past runs'. Also trigger when the user mentions trajectory analysis, run patterns, or evaluation score improvements.
Analyze financial health using ratio categories: profitability, liquidity, leverage, efficiency, and valuation. Use this skill when the user needs to assess a company's financial performance, compare companies, evaluate creditworthiness, or prepare financial due diligence — even if they say 'is this company financially healthy', 'analyze these financial statements', or 'compare these two companies'.
Apply the Fama-French three-factor model to decompose asset returns into market, size, and value factors. Use this skill when the user needs to explain cross-sectional return differences, evaluate fund performance beyond CAPM alpha, assess small-cap or value tilts in a portfolio, or when they ask 'why do small caps earn more', 'is value premium real', or 'what factors drive returns'.
Evaluate the performance of Triton operators on Ascend NPU. It is used when users need to analyze operator performance bottlenecks, collect and compare operator performance using msprof/msprof op, diagnose Memory-Bound/Compute-Bound bottlenecks, measure hardware utilization metrics, and generate performance evaluation reports.
HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distributed communication bandwidth, verifying HCCL functionality, and benchmarking collective operations like AllReduce, AllGather. Covers MPI installation, multi-node pre-flight checks (SSH/CANN version/NPU health), and production testing workflows.
Run system health checks including CPU, memory, disk, and process status. Use when: user asks about system performance, needs diagnostics, or wants to check resource usage. No API key needed.
Building decay and upkeep systems for survival games. Use when implementing timer-based decay, Tool Cupboard patterns (Rust-style protection radius), resource upkeep costs, or server performance management through automatic cleanup. Balances gameplay and server health.
MUST be used whenever optimizing a Dune app for speed, reducing render counts, improving CDF query efficiency, or reducing bundle size. Do NOT skip measurement steps — always profile before changing code. Triggers: performance, slow, laggy, optimize, optimization, re-render, bundle size, load time, Lighthouse, profiler, virtualization, lazy load, code split, CDF query, large list, memory leak.
Audit UI performance with Lighthouse and fix Core Web Vitals — LCP, CLS, INP. Fast UI is good UX. Use when optimising page load, fixing layout shift, reducing input delay, improving Lighthouse scores, or reviewing images, fonts, and render-blocking resources.
Enter this sub-process when conducting code optimization — handle tasks where 'behavior remains unchanged, structure changes' (structure / performance / readability). Shift single-module internal optimization from 'AI random refactoring' to 'first scan to generate a checklist, confirm each item with the user, execute step-by-step according to the method library, and require manual approval for each step'. Trigger scenarios: Users mention phrases like 'optimize it / refactor / rewrite / split it / poor performance / code is too long' without any accompanying behavior changes. Do not handle new requirements (route to feature), bugs (route to issue), or cross-module architecture restructuring (route to architecture + decisions).
Query OpenRouter for available AI models, pricing, capabilities, throughput, and provider performance. Use when the user asks about available OpenRouter models, model pricing, model context lengths, model capabilities, provider latency or uptime, throughput limits, supported parameters, wants to search/filter/compare models, or find the fastest provider for a model.