Results for “performance”

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Guides users through defining goals, metrics, and scope, then runs an autonomous loop of code changes, testing, measuring, and keeping or discarding results for any programming task with a measurable outcome.

Manage teams using Andy Grove's principles: production thinking for knowledge work, output indicators, managerial leverage, effective meetings, clean decisions, OKRs, and task-relevant maturity.

Extracts search performance data via the Google Search Console API v1 /searchAnalytics/query endpoint, analyzing CTR, impressions, and position trends with dimension filtering by page, query, device, and country.

Report the brand's organic performance from fb.ai — Search Console clicks/impressions/positions plus AI-engine visibility (whether ChatGPT, Perplexity and friends cite the brand). All traffic-monitor tools are free, so there is no quota gate. Run weekly or monthly.

Reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. This skill should be used when the user asks to review SwiftUI code, check for deprecated iOS/macOS APIs, validate data flow patterns, or audit accessibility compliance in Swift projects.

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.

TikTok Ads platform expertise. Audit campaigns, creative strategy, audience targeting, Spark Ads, TikTok Shop integration, pixel/Events API setup, and performance optimization. Use when the user asks about TikTok advertising, short-form video ads, TikTok Shop, Spark Ads, or social commerce advertising.

Design, implement, audit, and plan interface animation and motion systems. Use for animation reviews, motion audits, easing and duration decisions, gesture physics, transform origins, reduced-motion behavior, animation performance, SvelteKit or Motion integration, perceptual feel checks, or self-contained animation improvement plans.

Structured code review with a checklist covering correctness, clarity, tests, security, performance, and style. Use when reviewing a PR, diff, or set of code changes before merging — including phrases like "review this", "check my changes", or "is this ready to merge".

Convert Python code to idiomatic Roc. Use when migrating Python projects to Roc, translating Python patterns to idiomatic Roc, or refactoring Python codebases for type safety, functional purity, and native performance. Extends meta-convert-dev with Python-to-Roc specific patterns.

Systematically profile Node.js, Python, and Go applications to identify CPU, memory, and I/O bottlenecks, generate flamegraphs, analyze bundle sizes, optimize database queries, and run load tests with k6 and Artillery.

Generates DESIGN.md files for Google Stitch that encode premium, anti-generic UI standards with strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

Builds SOC performance metrics and KPI tracking dashboards measuring Mean Time to Detect (MTTD), Mean Time to Respond (MTTR), alert quality ratios, analyst productivity, and detection coverage using SIEM data.

Guides AI agents through Test-Driven Development with 42 prioritized rules covering the red-green-refactor cycle, test design, isolation, data management, assertions, organization, performance, and strategy.

High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.

Analyzes web page images for SEO and performance, checking alt text, file sizes, formats, responsive attributes, lazy loading, and CLS prevention, then produces an audit summary and prioritized optimization list.

Benchmarks energy-function-based safe control algorithms on the BIS (Benchmark of Interactive Safety) dataset, scoring safety, efficiency, and hybrid performance in human-robot and robot co-working scenarios.

Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use PROACTIVELY for debugging, incident response, or system troubleshooting.

Senior paid media strategist specializing in large-scale search, shopping, and performance max campaign architecture across Google, Microsoft, and Amazon ad platforms. Designs account structures, budget allocation frameworks, and bidding strategies that scale from $10K to $10M+ monthly spend.

Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.

Runs a side-by-side walk-forward backtest of a Bull Put Spread strategy with and without a FearScore entry signal, comparing performance metrics over ~8 years of daily data.

Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling.

Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).

Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform deployment. Handles gameplay systems, UI implementation, and platform optimization. Use PROACTIVELY for Unity performance issues, game mechanics, or cross-platform builds.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Plan and execute game QA including functional testing, playtesting, performance testing, compatibility testing, and bug tracking workflows. Use when setting up quality assurance for a game project. Also trigger for "game QA", "playtest", "bug tracking", "game testing", "QA plan", "regression testing", or "compatibility testing".

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Designs and iterates production-grade frontend interfaces, covering UX review, visual hierarchy, accessibility, performance, responsive behavior, theming, typography, layout, color, motion, and design systems. Handles websites, landing pages, dashboards, product UI, components, forms, and more.

Routes requests into the correct obsidian-mind mode: install, daily session loop, capture, review, maintenance, multi-agent wiring, or semantic search, using a ready-made Obsidian vault template for persistent agent memory.

Toolkit de alta performance para análise de intervalos genômicos em Rust com bindings Python. Use ao trabalhar com regiões genômicas, arquivos BED, tracks de cobertura, detecção de sobreposições, tokenização para modelos de ML, ou análise de fragmentos em genômica computacional e aplicações de aprendizado de máquina.

Evaluate everything the PA agent manages — tasks, skills, PA network health, billing, calendar connections, and memory quality. Use when: owner asks for an evaluation, wants to know what's working and what isn't, or requests a performance report. Combines supervisor status with quality scoring.

Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (gstack)

UTM parameter strategy, campaign tracking, and marketing attribution modeling. Build consistent UTM taxonomies, configure attribution models, measure cross-channel performance, and connect marketing spend to revenue. Use when the user asks about UTM parameters, campaign tracking, attribution models, marketing measurement, or cross-channel analytics.