Skill UI

Scores drafts for AI tells, removes robotic patterns, fixes rhythm and specificity, and injects brand voice before editing, then rescores the rewritten content.

A comprehensive system for creating high-conversion quiz and assessment funnels. This skill guides users through a 4-step process, from crafting irresistible landing pages (concept hooks) to designing structured questionnaires and automating follow-up sequences. It is specifically designed to generate qualified leads by tapping into prospects' dormant desires, achieving 30-50% conversion rates.

This skill analyzes proxy access logs, DNS query logs, and network flow data to identify unauthorized SaaS and cloud services (Shadow IT). It uses Python and pandas to aggregate traffic, classify domains against known SaaS categories, and calculate risk scores based on data volume and user count. Ideal for conducting thorough security audits and generating actionable remediation reports.

This skill establishes normal network communication patterns by analyzing historical NetFlow/IPFIX data. Utilizing Python pandas, it computes hourly/daily volume distributions, per-host statistics, and top-talker profiles. Anomalies are detected using sophisticated statistical methods like z-score and IQR, allowing SOC analysts to quickly identify deviations such as data exfiltration spikes, persistent beaconing, or unusual port usage.

This skill scores a scoped competitor set into comparable profile cards using nine weighted dimensions including positioning, voice, and visual craft. It provides evidence-anchored rubrics from 1-5 and a tension 2x2 plot. Use this when benchmarking competitors, building comparison matrices, or grading rival positioning before assembling reports. It ensures consistency by requiring the same evidence to earn the same score across all competitors.

A comprehensive guide for authors preparing a single-page academic rebuttal for top-tier AI conferences (e.g., CoRL). It details how to structure the response, focusing on maximizing impact through new, compact evidence (tables/figures) rather than verbose prose. Learn to triage reviewer comments, maintain a professional tone for public record, and optimize space for maximum score movement.

A comprehensive guide for authors drafting or revising academic papers for Web Conference (WWW). It teaches how to structure the paper around a web-native mechanism, quantify scale, and write for a mixed computing and social science audience. Learn best practices for page-one impact, compression, and stylistic details to maximize review scores.

This skill maps chronic conditions extracted from clinical notes to CMS-HCC V28 categories. It estimates the Risk Adjustment Factor (RAF) score, which is crucial for Medicare Advantage payments. It serves as decision support for coders by identifying candidate HCCs, applying complex coding hierarchies, and checking for MEAT documentation evidence for human validation.

This utility analyzes code changes within a branch compared to the base branch. It calculates a complexity score, detects scope coherence issues (warning if changes are too large or unrelated), and generates a fully structured Pull Request (PR) draft. It automates the creation of titles, comprehensive descriptions (including checklists and technical details), and even suggests splitting the PR into smaller, manageable units, significantly improving code review quality and efficiency.

Audits a website for compliance with Azerbaijan's Law on Personal Data and, where applicable, the EU GDPR plus ePrivacy/cookie rules. It inventories privacy documents, scores each requirement, and delivers a traffic-light executive summary plus a clause-level findings table with legal citations. Use for .az domains or sites targeting Azerbaijani or EU users.

An advanced tool that audits legal documents (such as contracts, NDAs, or policies) against established legal design principles. It scores the text across six pillars: language patterns, readability metrics (Flesch, LIX, etc.), structure, hidden clauses, statutory duplication, and visual hierarchy. It provides a non-rewriting assessment report to help users understand the clarity, complexity, and compliance risk of their legal drafting.

skill-doctor grades the performance and quality of an AI agent setup using real, local conversation history (e.g., Claude Code/Codex sessions). It scores skills against defined rubrics for efficiency and code quality, drafts evidence-backed suggestions for improvement, and generates a comprehensive, shareable local report. All processing is strictly local and private.