Skill UI

Python framework for multi-objective optimization, offering NSGA-II/III, MOEA/D, benchmark suites, customizable operators, and visualization to help engineering teams explore Pareto fronts and make multi-criteria decisions.

Use this command to set up a structured multi-agent collaboration environment within AgentHub. It allows you to define the core task, specify the required number of agents, and configure detailed evaluation criteria (metrics, directions, and commands) for both quantitative benchmarking and qualitative LLM judging. This is the starting point for any agent competition or complex AI workflow.

This skill initializes a new autoresearch experiment. It guides the user through defining all necessary parameters, including the domain, target files, evaluation commands, metrics, and optimization direction. It is the essential starting point for automated optimization and performance benchmarking cycles.

A comprehensive guide detailing best practices for hardening Docker containers, aligning with CIS Docker Benchmark v1.8.0. It covers host configuration, minimizing attack surface, implementing least privilege, and enhancing runtime security using techniques like read-only filesystems, Seccomp, and AppArmor. Use this when deploying secure, production-grade containerized applications.

This advanced skill guides users from a broad robotic concept (e.g., 'humanoid grasping') to a highly defined, research-ready hypothesis. It automates a robust four-stage pipeline: literature survey, idea creation, novelty verification, and critical review. The process rigorously enforces academic constraints, prioritizing simulation-first approaches, grounding ideas in established benchmarks (like ManiSkill or Habitat), and ensuring feasibility for real-world robotics development.

This comprehensive guide details industry best practices for container image hardening. It covers minimizing attack surface through multi-stage builds, utilizing distroless images, enforcing non-root users, and configuring read-only root filesystems. The techniques ensure compliance with standards like the CIS Docker Benchmark, making images secure and production-ready.

Run NVIDIA Cosmos Policy evaluations on LIBERO and RoboCasa simulations, enabling headless EGL GPU rendering, inference profiling, and benchmark workflows via public eval entrypoints.

Executes a structured VC valuation workflow that ingests SaaS or startup metrics, runs DCF, comparable revenue multiples, and SaaS health models via Python, and synthesizes a defensible valuation, runway, and capital-efficiency narrative for users planning fundraising or benchmarking.

A comprehensive 7-stage workflow designed to manage, audit, and optimize GitHub repositories. This tool automates critical tasks including identifying hardcoded secrets, cleaning up junk files, performing deep documentation reviews, benchmarking against competitors, and validating the final state, transforming messy codebases into production-ready assets.

A comprehensive tool for establishing performance baselines across multiple dimensions. It measures Core Web Vitals (LCP, CLS, INP), API latency (p50, p95, p99), and development build efficiency. Essential for detecting performance regressions before merging code, ensuring stability in CI/CD pipelines, and comparing alternative stack implementations.

This skill guides the comprehensive workflow for performance measurement in Go. It covers writing robust benchmarks using b.Loop(), running tests with advanced flags (CPU/memory profiles), and deep analysis using tools like benchstat and pprof. Use this when you need to precisely measure bottlenecks, statistically compare multiple optimization variants, or detect performance regressions in CI/CD pipelines.

A comprehensive guide for optimizing Golang applications, covering systematic approaches to identifying and resolving bottlenecks. It details best practices for reducing memory allocations, improving CPU efficiency, tuning GC, and managing concurrency. The methodology emphasizes profiling first (using pprof, fgprof) and following an iterative cycle: Benchmark → Diagnose → Improve → Benchmark.