Loading...
Loading...
Found 201 Skills
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
Multi-cycle performance optimization with profiling and bottleneck analysis. Use when optimizing application performance.
Correlates performance targets with actual profiling results. Identifies bottlenecks and validates against non-functional requirements.
Implement Documenso rate limiting, backoff, and request throttling patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Documenso. Trigger with phrases like "documenso rate limit", "documenso throttling", "documenso 429", "documenso retry", "documenso backoff".
Evidence-based memory optimization from real usage patterns. Analyzes recall performance, identifies bottlenecks, suggests consolidation/pruning/enrichment, and tracks improvement over time via checkpoint Q&A.
Apply Theory of Constraints (TOC) to identify and manage system bottlenecks. Use this skill when the user needs to find what limits throughput, optimize a constrained process, apply the Five Focusing Steps, or implement Drum-Buffer-Rope scheduling — even if they say 'our output is stuck', 'what's the bottleneck', or 'why can't we produce more'.
Industry supply-chain analysis via Longbridge Securities — maps upstream / midstream / downstream structure for a sector, identifies key bottleneck nodes, assesses bargaining power and profitability at each tier, and evaluates investment value of core supply-chain companies using Longbridge data. Triggers: "产业链", "供应链", "上中下游", "产业链分析", "供应链分析", "咽喉环节", "卡脖子", "产业链投资", "产业链研究", "產業鏈", "供應鏈", "上中下游", "產業鏈分析", "供應鏈分析", "咽喉環節", "supply chain", "value chain", "upstream midstream downstream", "supply chain analysis", "bottleneck", "industry chain", "supply chain investment".
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
Diagnose ClickHouse disk usage, compression efficiency, part sizes, and storage bottlenecks. Use for disk space issues and slow IO.
Profiles DAG execution performance including latency, token usage, cost, and resource consumption. Identifies bottlenecks and optimization opportunities. Activate on 'performance profile', 'execution metrics', 'latency analysis', 'token usage', 'cost analysis'. NOT for execution tracing (use dag-execution-tracer) or failure analysis (use dag-failure-analyzer).
GPU kernel profiling workflow across supported kernel implementation languages. Provides commands for all 4 profiling modes (annotation, event, ncu, nsys), metric interpretation tables, bottleneck identification rules, and the output contract for returning compact results to the orchestrator. Use when: (1) profiling a kernel version, (2) interpreting profiling artifacts/reports, (3) comparing kernel versions, (4) identifying bottlenecks and optimization opportunities, (5) documenting performance in the development log.