Skill UI

This skill analyzes existing legacy codebases to detect implicit coding conventions across four meta-architectural dimensions (File Anatomy, State & Control Flow, Infrastructure, Error Handling). It resolves conflicts one by one with the user, generating a structured rules file (.ai-style-rules.md) and optionally installing persistent hooks to prevent AI-generated code style drift in future development.

A comprehensive guide for engineering and optimizing latency-sensitive systems. Essential for real-time dashboards, market data feeds, streaming agents, and high-frequency infrastructure where p95 latency, data freshness, and throughput are critical metrics. Covers hot path mapping, performance optimization strategies, and robust verification guardrails.

This skill guides users through Phases 2 (Pseudocode Design) and 3 (Architecture Design) of the SPARC methodology. It translates high-level specifications into detailed technical blueprints, covering algorithm pseudocode, module boundaries, API contracts (using DDD patterns), and infrastructure planning, ensuring a robust plan before writing production code.

A comprehensive reference for managing Uncloud, a decentralized self-hosting platform. This guide details using the `uc` CLI to deploy services, configure Caddy ingress, manage ports (HTTP/HTTPS/TCP/UDP), scale workloads, and inspect logs across a WireGuard mesh cluster. Ideal for setting up resilient, self-owned microservices infrastructure.

This comprehensive guide provides expert protocols for writing the 'Related Work' section in Machine Learning papers. It teaches authors how to maintain 'versioned honesty' by meticulously triaging the literature into distinct lanes (e.g., method lineage, model artifacts, evaluation infrastructure). It covers advanced topics like managing concurrent work, citing arXiv status accurately, and avoiding self-citation violations, ensuring the paper is positioned rigorously within the rapidly evolving academic field.

This guide helps authors position their machine learning systems manuscripts for the rigorous Conference on Machine Learning and Systems (MLSys). It details the venue's specific focus on system-level contributions, including training/inference infrastructure, compilers, data systems, and hardware-aware ML. Learn how to frame your work to appeal to systems reviewers by emphasizing measurable impacts on capability, cost, reliability, or deployment scale.

This guide provides comprehensive standards for designing, auditing, and documenting AI experiments for major conferences like IJCAI. It covers establishing strong baselines, conducting ablation studies, and reporting meticulous details on hyperparameters, computational infrastructure, and ethical risks, ensuring maximum reproducibility and academic credibility for AI research.

A comprehensive audit checklist for submitting academic papers to the ACM IMC conference. It covers critical details including double-blind anonymity (scrubbing infrastructure leaks), mandatory Ethics declarations (IRB/Belmont), proper formatting (BBL, acmart), page limits, and cycle planning to minimize desk-reject risks.

This guide provides detailed guidelines for authors submitting to top-tier formal methods conferences (like TACAS). It emphasizes moving beyond simple literature summaries by employing a "delta-first" approach. Authors must precisely position their algorithm or tool by contrasting its novel features, guarantees, or scaling benefits against the nearest prior work, while also crediting underlying infrastructure and covering major verification venues.

This skill provides a comprehensive guide for authors targeting the USENIX Symposium on Operating Systems Design and Implementation (OSDI). It helps in positioning complex systems research, covering core scope areas like operating systems, distributed systems, and cloud infrastructure. It details how to frame the contribution, build evidence (artifacts, baselines), and distinguish the work from similar top-tier venues like SOSP and NSDI.

This workflow performs a comprehensive review against the Azure Well-Architected Framework (WAF) using your existing Infrastructure as Code (IaC) and deployed resources. It systematically checks the five pillars—Reliability, Security, Cost Optimization, Operational Excellence, and Performance Efficiency—identifying architectural risks, drift, and compliance gaps. Findings are automatically logged and converted into actionable GitHub issues for streamlined remediation.

A specialized downstream skill for CTF-sandbox workflows. Used to analyze complex security challenges driven by AI agent interactions, prompt injection, or infrastructure vulnerabilities. Focuses on tracing control chains involving untrusted input, tool side effects, deployment drift, container runtime issues, and CI/CD supply chain provenance. Ideal for rigorous vulnerability assessment in modern, distributed systems.