Skill UI

This skill acts as a comprehensive guide for authors targeting the USENIX Symposium on Networked Systems Design and Implementation (NSDI). It helps authors assess the fit of their research in networked, distributed, or cloud systems, providing strategic advice on paper reframing, required levels of evidence (e.g., real-scale deployment), and accurate positioning relative to closely related conferences like OSDI and SIGCOMM. It is a critical tool for optimizing conference submission chances.

This comprehensive guide provides researchers with structured methodologies for designing and auditing Computer Vision (CV) experiments for major conferences like WACV. It details the critical differences between the Applications and Algorithms tracks, emphasizing the need to report performance under real deployment constraints (e.g., power, latency) and ensuring fair, rigorous comparisons with baselines. Ideal for revising submissions to meet high review standards.

Scans your local machine's Git history to locate abandoned or unfinished side projects. It performs a deep 'autopsy' on these repositories, determining their causes of death (e.g., deployment fear, killed by newer ideas) and identifying personal developmental patterns. The tool then surfaces the most promising candidate for resurrection, helping you finally ship it.

The Azure CLI command group for managing Azure Container Registry (ACR). This tool allows users to perform the entire ACR lifecycle, including creating registries, authenticating credentials, building and pushing container images (using cloud builds), importing images from other sources, and configuring advanced features like geo-replication, private endpoints, and webhooks. Essential for CI/CD pipelines and container deployment workflows in Azure.

Provides a comprehensive, quantitative auditing system for AI agents, skills, and commands. It evaluates these components against industry best practices using a multi-criteria weighted scoring model and assign a production readiness grade (A-F). Ideal for validating complex AI systems before deployment, identifying gaps, and ensuring robust, maintainable code.

This skill audits OpenMed NER or de-identification models to detect performance disparities across sensitive demographic subgroups (e.g., sex, age, race). It calculates metrics like per-group recall and leakage disparity, helping users identify instances of 'under-protection' before deployment, ensuring equitable AI governance and compliance.

This skill automates the creation of comprehensive Model Cards for OpenMed clinical NER or de-identification models. It gathers data from various OpenMed evaluation reports (e.g., `GateReport`, `fairness_report`, `error_report`) to structure critical governance information, including intended use, quantitative performance metrics, subgroup analysis, limitations, and required medical-device disclaimers. It ensures documentation is reproducible and compliant for clinical AI deployment.

This tool benchmarks the recall of PII detection models, crucial for ensuring privacy compliance before deployment. It uses synthetic fixtures and enforces a recall floor by measuring label-aware exact-span and grapheme recall against predefined gold standards. It is essential for auditing models and preventing critical privacy leaks.

A powerful post-deployment monitoring tool designed for continuous quality assurance in CI/CD pipelines. It captures a performance baseline before deployment and then continuously monitors live applications after deployment. It alerts on critical failures (e.g., 5xx errors), performance regressions, and unexpected changes, ensuring that new releases maintain production stability.

Quickly retrieve and display the current Continuous Integration/Continuous Deployment (CI/CD) pipeline status for the active branch or a specific Pull/Merge Request. This tool supports major Git platforms including GitLab CI and GitHub Actions, providing developers with an immediate snapshot of build and test results.

A comprehensive white-box security auditing workflow designed for proprietary source code. It integrates static analysis security testing (SAST) tools like Semgrep and CodeQL to detect common vulnerabilities (e.g., injection, IDOR, crypto misuse), followed by mandatory manual threat modeling and verification steps. Applicable for PR reviews and pre-deployment security checks.

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.