my-claude

Drive performance optimizations through a disciplined measure-optimize-measure cycle. Write benchmarks first, optimize with data, and validate improvements empirically. Use when building performance-critical code paths, lock-free structures, or when performance requirements are quantified.

Prevent false sharing in concurrent Rust code by aligning data structures to cache-line boundaries. Critical for lock-free data structures and multi-threaded hot paths. Use when building multi-threaded code with shared atomics or lock-free structures.

Document decisions, challenges, and solutions immediately after completing each phase. Captures context that would be lost later, creates invaluable reference for future work. Use for complex projects with non-obvious design decisions or any project taking more than 1 week.

Test and validate after each component/phase instead of waiting until the end. Catches bugs early when they're cheap to fix, prevents cascade failures. Use when building complex systems with multiple components where components depend on each other.

Measure sub-microsecond latencies using architecture-specific timestamp counters (TSC) and wait-free histograms. Essential for real-time systems, HFT, and latency-sensitive applications. Use when sub-microsecond latency requirements exist or when P99/P95 percentile analysis matters.

Layer different test types (unit, property, concurrency, stress, benchmark) to catch different bug classes. Each level catches what others miss. Use for complex systems, concurrent/parallel code, or performance-critical applications.

Launch multiple specialized Claude agents simultaneously to maximize productivity. Achieves 3-5x speedup on independent tasks like benchmarking, documentation, and analysis. Use when you have multiple independent tasks that each take more than 1 minute.

Set up comprehensive performance profiling using Criterion benchmarks, flamegraphs, and custom TSC-based measurements to identify bottlenecks and validate optimizations. Use for performance-critical applications, sub-microsecond latency requirements, or lock-free data structures.

Break complex projects into detailed multi-phase plans before writing any code. Prevents scope creep, refactoring waste, and missed requirements. Use when starting any project with more than 1000 lines of code or building systems with multiple interacting components.

Validates CI/CD configurations, runs CI checks locally, and debugs failures to ensure everything passes correctly in the Arda ecosystem. Use when validating CI pipelines, debugging CI failures, or ensuring CI passes before merging.

Comprehensive commit workflow that builds projects, runs tests, linters, and formatters, then creates semantic commits following organizational standards. Use when committing code changes to ensure quality, consistency, and proper commit message formatting.

Semantic search across credit documentation using 4096-dimensional embeddings (Qwen3-Embedding-8B). Enables natural language queries to find relevant clauses, covenants, terms, and structures across assignments, credit agreements, fee letters, security agreements, and other credit documents. Use when searching credit documentation, researching precedents, extracting covenant structures, or analyzing collateral packages.

Deep discourse analysis of credit market documents using InfraNodus text network analysis. Transforms document collections into knowledge graphs, revealing conceptual relationships, thematic clusters, structural gaps, and research questions. Use when analyzing credit documentation, developing investment theses, conducting due diligence, or synthesizing market intelligence.