876 skills · sorted by relevance
Review SGLang Cookbook pull requests for configuration errors, documentation mismatches, benchmark issues, and broken links. Get findings for each file and an overall recommendation on whether to approve, request changes, or block the contribution.
Explain portfolio performance by separating the effects of sector allocation, stock selection, market factors, and timing. Compare results with a benchmark, assess risk-adjusted returns, and prepare a report showing where excess returns came from.
Analyze social media post data to calculate engagement, click rates, and estimated returns on advertising spend. Compare results with supplied platform benchmarks, identify strong and weak posts, and generate recommendations for improving campaign performance.
Create, update, run, and debug shell-based performance scenarios for the but CLI. It separates repository setup from the operation being measured, uses Hyperfine for timing, and guides focused validation and inspection of test output.
Turn a broad robotics research direction into ranked ideas with concrete benchmarks and simulation plans. The workflow combines literature review, novelty checks, and external critique while accounting for hardware access, safety, evaluation metrics, and failure cases.
Build Go services and command-line tools with clear interfaces, explicit error handling, and concurrent tasks using goroutines and channels. Use pprof to investigate performance, then check behavior with benchmarks, structured test cases, fuzzing, and race detection.
Run concurrent Omnigent conversations with real hosts and runners while replacing the LLM with a zero-latency mock. Read the generated report to explain response-time distributions, throughput, and failures, helping assess Omnigent's own processing overhead.
Refresh evidence behind paid advertising guidance by checking platform changes, APIs, policies, regulations, and benchmarks. Record sources and contradictions, flag outdated or unsupported claims, and propose updates grounded in current primary sources.
Evaluate a local Codex skill for metadata, structure, reference links, size, and helper code quality. Get prioritized fixes and explanations, with benchmark setup for deeper analysis and measurement recommendations when observed usage is available.
Evaluate a local Codex plugin to understand its scores and identify what to fix first. Review stronger and weaker skills, prepare benchmark runs, compare saved results across versions, and produce a readable report.
Investigate observed slowdowns or increased CPU, memory allocation, and IO costs in a process you control. Use controlled timing and runtime-specific profiling tools to test a cause, then check performance and behavior after a fix.
Compare baseline and current Pinot benchmark results from JMH, a tool for measuring code performance. The skill uses a separate baseline worktree, a working directory kept apart from the current code.
Optimize .NET loops with SIMD, which processes multiple values in one operation, or review existing SIMD code. Check behavioral equivalence, memory safety, platform fallbacks, and benchmarks to establish whether the optimization is correct and worthwhile.
Runs HTTP load tests with gradually increasing concurrent connections. It measures response-time percentiles, throughput, and errors, identifies where performance starts to deteriorate, and recommends a concurrency level based on the results.
Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.
Improve vllm-mlx performance through research, small experiments, and benchmarks on real models. The skill records results, keeps changes that improve measured performance, and carries successful work through implementation, testing, review, and pull request creation.
Benchmark indicator performance with BenchmarkDotNet. Use for Series/Buffer/Stream benchmarks, regression detection, and optimization patterns. Target 1.5x Series for StreamHub, 1.2x for BufferList.
The English summary is being prepared. Showing the original description.
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
The English summary is being prepared. Showing the original description.
Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, comparing library and benchmark configs, resizing parallelism for a GPU allocation, or distinguishing convergence changes, semantics-preserving execution tuning, and benchmark-only shortcuts.
The English summary is being prepared. Showing the original description.
Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
The English summary is being prepared. Showing the original description.
Golang performance optimization patterns and methodology - if X bottleneck, then apply Y. Covers allocation reduction, CPU efficiency, memory layout, GC tuning, pooling, caching, and hot-path optimization. Use when profiling or benchmarks have identified a bottleneck and you need the right optimization pattern to fix it. Also use when performing performance code review to suggest improvements or benchmarks that could help identify quick performance gains. Not for measurement methodology (→ See `samber/cc-skills-golang@golang-benchmark` skill) or debugging workflow (→ See `samber/cc-skills-golang@golang-troubleshooting` skill).
The English summary is being prepared. Showing the original description.
Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.
The English summary is being prepared. Showing the original description.
Run all reference benchmarks under benchmarks/eval/ and refresh the reference-table cells in benchmark_*.py. Auto-detects host hardware (H200/H100/H800/...). For each row's matching hw entry: replace cells in place. For new hardware or a new workload tag: append a new row to the section's table. Local-Pipeline-Result tables are skipped. One slash command runs everything end-to-end and auto-commits.
The English summary is being prepared. Showing the original description.
**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison. DO NOT USE FOR: improving skill frontmatter (use waza dev), creating new skills from scratch (use skill-creator), token counting or budget checks (use waza tokens). INVOKES: Copilot SDK executor, mock engine, code/regex validators. FOR SINGLE OPERATIONS: use waza run directly for a single benchmark.
The English summary is being prepared. Showing the original description.