Loading...
Loading...
Found 7 Skills
Expert at quality-focused code review with security emphasis. Use when reviewing code changes, performing security audits, identifying bugs, ensuring code quality and maintainability, or analyzing pull requests for issues.
Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality, and test coverage analysis with confidence scoring and actionable recommendations.
Company HR specialist providing expert guidance on job descriptions, interview processes, candidate evaluation, onboarding, performance management, and HR policies. Use when working on human resources tasks and people operations.
Comprehensive code review criteria covering correctness, readability, maintainability, security, performance, and testing. Reference when reviewing code changes or preparing code for review.
Analyze candidate algorithms for time/space complexity, scalability limits, and resource-budget fit (CPU, memory, I/O, concurrency). Use when feasibility depends on input growth or latency/memory constraints and quantitative bounds are required before implementation; do not use for persistence schema or deployment topology decisions.
Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.
Maintain JSONL-only profiler performance test cases under csrc/ops/<op>/test in ascend-kernel. Collect data using torch_npu.profiler (with fixed warmup=5 and active=5), aggregate the Total Time(us) from ASCEND_PROFILER_OUTPUT/op_statistic.csv, and output a unified Markdown comparison report (custom operator vs baseline) that includes a DType column. Do not generate perf_cases.json or *_profiler_results.json. Refer to examples/layer_norm_profiler_reference/ for the reference implementation.