В каталоге 182 820 навыков в 14 категориях.
Measure API latency, bundle size, and database query time, and compare them against saved baselines to catch performance...
Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total tokens,...
Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
Use when you need measured performance evidence by running a repeatable command on the current branch and a baseline ref
Performance baseline and regression detection
Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, an...
Compare Claude Code output with full config vs minimal config using standardized tasks per stack.
Measure performance baselines and detect regressions across browser Core Web Vitals (LCP, INP, CLS, page weight), API en...
Measure performance baselines
Performance regression detection using the browse daemon. (gstack)
Replaces guesswork with empirical hardware telemetry: synthesizes ad-hoc stress-test harnesses on the fly, executes them...
Use when choosing between engines or models for an agent pipeline and the answer must come from measurement on your own...
Run each collector script against its fixture, measure time and output size, detect regressions. Trigger: /benchmark
Skill for the Benchmark area of Securacy. 7 symbols across 3 files.
Benchmark HBF performance using Apache Bench (ab). Measures static asset serving, versioned filesystem operations, and Q...
Performance regression detection. Captures TTFB, FCP, LCP, bundle sizes, request counts. Regression thresholds: timing >...
Local-only regression / benchmark skill for ui-clone-skills maintainers. Drives the standard ui-reverse-engineering pipe...
基于 browse daemon 的性能回归检测。建立页面加载时间、Core Web Vitals、 资源体积的基线，并在 PR 前后做对比。 (gstack)
Classify offline RL datasets by D4RL challenge properties and explain benchmark implications from metadata.
Assemble executable posteriordb reduced benchmark recovery runs with provenance, metric, and mechanism evidence.
Suggests which benchmarks to run based on code changes
Takes one of the user's own metrics and checks it against a stated benchmark source, returning a clear over/under read a...
Marketing benchmark triage skill. Use whenever metrics are shared with questions like "is this good?", "is this normal?"...
ユーザーが「ベンチマーク実行」「パフォーマンス測定」「性能分析」「速度を測って」「ベンチマークして」等と要求した時に発動。 Go benchmarkを実行し、結果を分析してボトルネックを特定し、改善提案を行う。 既存のベンチマークがない場合...
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before...
Design, review, or report a measured performance comparison. Use for benchmark methodology, speedup or regression claims...
Vet a performance measurement or design a fair comparison before using a speedup, regression, throughput, or latency num...
Use when checking measured benchmark claims.
Installable benchmark cleanup skill bundle for OpenClaw / DebateClaw / ChemQA benchmark runs. Use when benchmark scripts...
End-to-end benchmark suite for vercel-plugin. Runs realistic projects through skill injection, launches dev servers, ver...
Fetch benchmark performance data from 6 leaderboard websites using Playwright MCP and update model manifests with the la...
Measure function performance and compare implementations. Use when optimizing critical code paths.
Use for JS/TS performance-sensitive changes, benchmark additions, benchmark regressions, benchmark result JSON, or any c...
Benchmark and evaluation harness for Mistral Large on heavy codebase, large-context (chonk), and multi-file refactoring...
Standardized compliance QRA benchmarks against candidate LLMs
Cross-model benchmark. Runs one prompt or skill through Claude, GPT (Codex CLI), and Gemini side by side and compares la...
Cross-model benchmark for gstack skills. (gstack)
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-si...
Benchmark Neovim startup time and identify slow plugins or configurations
Profile Ollama LLM prefill/decode TPS across short text, long prompts, and vision+text inputs. Handles API routing, metr...
Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluat...
Benchmark an OpenMed PII model with synthetic gold spans and report label-aware exact-span and grapheme recall without e...
Benchmark the production Qwen 3.6 35B-A3B MTP llama.cpp service and real Pi Agent latency. Measures cold-KV prefill TPS,...
Measure the FPS and GPU frame time impact of a rendering pass, FBO, shader or other rendering change in Hypersomnia by A...
Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documenta...
Multi-step workflow for running performance benchmarks on ccswarm.
Create benchmark suite creator operations. Auto-activating skill for Performance Testing. Triggers on: benchmark suite c...
Benchmark Suite Creator - Auto-activating skill for Performance Testing.Triggers on: benchmark suite creator, benchmark...
Quick-start command to run SWE-bench Lite evaluation with sensible defaults.
Parse small benchmark markdown tables from paper notes and summarize datasets, metrics, and best-performing methods.
Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and indep...
Benchmark and attribute zsh startup and prompt latency. Use when asked to profile a slow zsh prompt, explain where shell...
Go benchmarking for measuring and optimising code performance
性能基准测试
Benchmarking and competitive analysis techniques. Compares performance, processes, and practices against industry standa...
Performance benchmarking practices using pytest-benchmark. Activated when working with benchmarks, performance testing,...
Score an OpenMed clinical or biomedical NER model against a user-supplied gold corpus with entity-level precision, recal...
Nutzt Marktvergleiche vorsichtig für Rates, Gehälter, Profitabilität und Größe. Für Managing Partner, Management Committ...
Improve content for answer engines and AI-assisted search through evidence-rich direct answers, clear entity/topic struc...
Bence's code style, tech stack, and workflow conventions
Expert UI/UX design guidance for unique, accessible interfaces. Use for visual decisions, colors, typography, layouts. A...
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to...
Prove selected properties of Bend modules when a plan has chosen Bend proof work, the user explicitly requests it, or an...
When the user wants to solve a structured MILP or two-stage stochastic program by Benders decomposition — splitting it i...
Expert reference for beneficial ownership data, policy, and BODS. Trigger on: BODS JSON/schema/tools (bodsdata, CoVE-BOD...
Audit the beneficiary designations that quietly override wills — the account-by-account sweep, the life-event triggers t...
Consultar benefícios sociais por CPF (Bolsa Família, BPC, CadÚnico)
Designs and runs employee benefits and leave — health and retirement plans, leave policy, cost and renewal, and the admi...
Check whether a raise, more hours, or a new job could cost you more in lost benefits than you gain — the 'benefits cliff...
Decode an employment benefits package into what it's actually worth and where the fine print bites. Use when someone ask...
Tracks promised benefits after go-live using a Benefits Dependency Network that traces each benefit back to the business...
Ensures projects deliver the value they were approved on — defining measurable benefits, baselining, tracking after deli...
Submit expense reimbursements through Benepass (app.getbenepass.com). For users whose employer uses Benepass as their be...
Bengali (Bangla) text processing patterns including Unicode normalization, script detection, tokenization, conjunct hand...
Audit a week the way Arnold Bennett's 'How to Live on 24 Hours a Day' (1908) prescribes — time as the one income that ca...
Draft or judge content in Ben van Sprundel's voice. Use EVERY TIME output is written as Ben or scored against his tone -...
Writes and edits content in Ben Swift's distinctive voice for any type of writing including blog posts, emails, technica...
当 Bensz Agent Skill 或基础设施本身因设计缺陷出现问题，或用户明确要求记录/上报此类 bug 时使用。⚠️ 不适用：用户数据错误、第三方服务故障、用户主动改源码或模型偶发波动。
当主要交付物是可复用的 R 函数、稳定 API、S3/S4/R6 类或 R Package，需要设计、开发、重构或审查其接口、测试、文档、并行与性能边界时使用。分析项目中只有需要跨分析复用或形成公共 API 的组件才进入本 Skill。⚠️...
当主要交付物是基于 R 的数据分析流程、科学结果、可复现数据产品、R Markdown/HTML 报告或论文级图表与解读时使用；即使流程中包含 `.R` 脚本和仅服务当前分析的辅助函数，也由本 Skill 主导。⚠️ 不适用：主要交付物是可...
Modular grid layout with card-like blocks, clear hierarchy, soft spacing, and subtle visual contrast for organized, scan...
Apple-style bento grid with modular cards, frosted glass touches, and soft depth.
当使用者说"做一张苹果发布会那种总结图""bento 图""把卖点、功能或研究成果排成一张格子图""产品亮点一图看完""做成竖版发小红书"时使用。先出内容清单和线框预览，确认后由脚本排版，用本机 Chrome 渲染成 PNG：主图居中，四周...
Create and edit Bento presentations — single-file .bento.html decks whose document is plain JSON in a "#bento-doc" scrip...
Web and App implementation guide for Bento UI. Trigger when user wants modular grid cards, Apple-like dashboard style, o...
BentoML skill for model packaging, serving, and containerization.
Automate Benzinga tasks via Rube MCP (Composio). Always search tools first for current schemas.
Beoordelingshandleiding voor Open-ICT studenten. Gebruik bij het beoordelen, evalueren of geven van feedback op vaardigh...
Develops BepInEx plugins with hooks, patches, and mod initialization for Unity games. Use when: Creating BepInEx plugins...
AI job-search coach for Berlin and the rest of Germany. Searches live postings (Bundesagentur für Arbeit API, Arbeitnow,...
Create contemporary anime-style images or prompts from photos or described scenes, preserving identity, age, and composi...
Create claymation-style still images or prompts from photos or scenes, using chunky matte plasticine forms and visible h...
Create intentionally awkward MS Paint-like scribble images or prompts from photos or subjects, using shaky lines, crude...
Create Western comic-book images or prompts from photos or scenes, using hand-inked contours, varied line weights, and h...
Create minimal pastel crayon sketches or prompts from photos or described subjects, with broken wax contours and generou...
Create sparse cut-paper collage images or prompts from photos or subjects, using a few semantic anchors and large areas...
Create cyanotype-style images or prompts from photos or subjects, using Prussian-blue fields, cream-white silhouettes, a...
Create intaglio etching-style images or reusable prompts from a subject or reference photo, using fine copper-plate line...