881 skills · sorted by relevance
Integrate a supported object detection model from HuggingFace or NVIDIA NGC into NVIDIA DeepStream. Automates model acquisition and conversion, TensorRT engine building, detection output parsing, multi-stream performance benchmarks, and reports with charts in Markdown, HTML, and PDF.
Build English clinical speech-recognition benchmarks by selecting medical terms, checking pronunciations, and generating synthetic audio. Outputs include audio files and a NeMo manifest, a structured file listing recordings and metadata, ready for a separate scoring stage.
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.
Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts. Use when a developer wants a baseline, wants to compare before and after changes, asks to measure build performance, mentions build times, build duration, how long builds take, or wants to know if builds got faster or slower.
The English summary is being prepared. Showing the original description.
Routes any legal task to the right LLM, like OpenRouter but for legal work and grounded in benchmarks instead of brand loyalty. Built from mid-2026 legal evals (legalbenchmarks.ai, Vals AI × Stanford LegalBench across 124 models, Harvey's Legal Agent Benchmark, the Atticus Project's CUAD/MAUD/ACORD) plus translation evidence (WMT25, SwiLTra-Bench, ArabLegalEval). Covers five verticals: contract drafting, info extraction, legal research, contract review, and legal translation (including Arabic/MENA). Each asks up to four questions (cost, speed, accuracy/stakes, privacy/jurisdiction/language), then returns a primary model, a fallback, what to avoid, and what a human must verify. Core principle: capability is not controllability, so every route ends with a verification step. Not legal advice; a lawyer owns the output.
The English summary is being prepared. Showing the original description.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
The English summary is being prepared. Showing the original description.
Create original surveys, benchmarks, and aggregated data nobody else has. Automate data collection for content moats. Triggers on: "create original data", "proprietary data", "survey design", "benchmark study", "original research", "data-driven content", "create a survey", "industry benchmark", "aggregated data", "unique data", "first-party data", "data moat", "generate research data", "create a study", "original statistics", "data nobody else has", "competitive data advantage".
The English summary is being prepared. Showing the original description.
Use when evaluating a newly adapted model's accuracy/eval score. Runs evalscope eval (or the test/srt/run_eval.py fallback) against an OpenAI-compatible endpoint on datasets like gsm8k / aime, producing per-dataset reports and a score. Accuracy only — throughput/latency benchmarks belong to model-speed-benchmark. Triggers on accuracy, eval, evalscope, gsm8k, aime, run_eval — not throughput.
The English summary is being prepared. Showing the original description.
Use when running throughput/latency (serving speed) benchmarks against an already-running model server. Uses sgl_jax.bench_serving to sweep batch-size/concurrency and measure throughput and latency, producing summary.csv and per-point bs_<N>/result.jsonl. Speed only — accuracy/eval belongs to model-accuracy-benchmark. Triggers on throughput, latency, bench_serving, batch-size sweep, tok/s, TTFT, TPOT — not accuracy/eval.
The English summary is being prepared. Showing the original description.
Guides privacy program maturity assessment using the AICPA/CIPT Privacy Maturity Model with five levels: Ad Hoc, Repeating, Defined, Managed, and Optimized. Covers assessment methodology across ten privacy domains, scoring criteria, gap analysis, maturity roadmap generation, and benchmarking against industry peers. Keywords: privacy maturity, AICPA, maturity model, assessment, roadmap, benchmarking.
The English summary is being prepared. Showing the original description.
Guides privacy program effectiveness measurement including leading and lagging indicators, KPI definition, benchmarking methodology, executive reporting formats, board-level privacy dashboards, and metric-driven program improvement. Covers operational, compliance, risk, and strategic privacy metrics across the program lifecycle. Keywords: privacy metrics, KPIs, benchmarking, executive reporting, dashboard, program effectiveness.
The English summary is being prepared. Showing the original description.
从公开内容中筛选真正值得学习、能够迁移的对标样本，并排除名人效应、粉丝体量和独特资源造成的假象。用户要找低粉爆款、垂直对标、邻近受众样本或跨赛道灵感时使用。 English: Find public benchmark content that is genuinely learnable and transferable while filtering out celebrity effects, follower-size bias, and unique-resource noise. Use for low-follower breakout posts, niche benchmarks, adjacent audiences, or cross-category inspiration.
The English summary is being prepared. Showing the original description.
Benchmark Email integration. Manage data, records, and automate workflows. Use when the user wants to interact with Benchmark Email data.
The English summary is being prepared. Showing the original description.
Compare WOZCODE vs vanilla Claude Code on the user's codebase — real cost, turn, and time savings. TRIGGER on "compare woz", "how much does woz save", "benchmark woz", "woz vs claude", "show me savings", or /woz-benchmark.
The English summary is being prepared. Showing the original description.
Peer benchmarking, multi-ticker financial comparison, growth value matrix, composite z-score ranking, industry peer comparison, competitive benchmarking, sector relative performance, peer group analysis, industry leader comparison, financial ratio benchmarking
The English summary is being prepared. Showing the original description.
Generates and executes load test scripts for APIs using k6, wrk, or autocannon. Creates realistic test scenarios from OpenAPI specs, route files, or endpoint descriptions. Use when someone needs to load test, stress test, benchmark, or find the breaking point of their API. Trigger words: load test, stress test, benchmark, RPS, concurrent users, breaking point, performance test, k6, wrk.
The English summary is being prepared. Showing the original description.
用户要找对标账号/分析竞品爆款/找差异化选题时;或问"怎么做AI工具赛道的差异化""how to find benchmarks / differentiate"时。按5步走:找3-5个低粉高爆对标(搜索from:xxx min_faves:10)→分析90天爆款抓隐性需求→学互动策略→拆变现模式→三公式变形(场景细化/人群聚焦/观点反转)出差异。不适用于:已有定位日常发内容(→x-short-content-craft)、纠结选IP还是泛流量(→x-positioning-tradeoff)、检查草稿(→x-five-piece-checklist)、纯信息查询。
The English summary is being prepared. Showing the original description.
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
The English summary is being prepared. Showing the original description.
Evaluates fund performance against peer universes with vintage year comparison, quartile ranking, and strategy-specific benchmarking. Use when benchmarking fund performance, analyzing vintage comparisons, or assessing relative positioning.
The English summary is being prepared. Showing the original description.
Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits (scaffold, cold-start, temporal, combination), evaluator metrics, benchmark groups, and bounded molecular-oracle workflows. Use this skill to find which TDC datasets exist for a therapeutic task, load them with a split that does not leak, score predictions with the task's own official metric rather than a generic one, and run benchmark groups reproducibly. Also trigger on PyTDC, Therapeutics Data Commons, tdc.single_pred, tdc.multi_pred, ADMET Benchmark Group, scaffold split, get_split, or molecular oracles such as GSK3B, JNK3 and DRD2.
The English summary is being prepared. Showing the original description.
Select an OCR/HTR engine by benchmarking candidates on the same labelled samples — source ground truth from open datasets (e.g. Hugging Face PAGE-XML corpora) or hand-transcription, wrap every engine behind a transcribe(image_path) -> str adapter (vision-LLMs via any OpenAI-compatible endpoint, dedicated HTR REST APIs, cloud OCR), and score with zero-dependency raw CER, lenient CER, WER, and a critical name/date token diff. Use when choosing an engine for handwriting or historical-document transcription, when published accuracy claims need honest verification on your own material, or when a records workflow must surface confident-but-wrong names and dates that a low aggregate CER hides.
The English summary is being prepared. Showing the original description.