Skill UI

This skill autonomously polishes and improves generated scientific papers through multiple expert AI review cycles. It simulates a professional revision process: expert review (using GPT-5.4) → implementing structural and theoretical fixes → recompiling the LaTeX document. It is designed to enhance writing quality, address inconsistencies, refine claims, and improve overall presentation, making it ideal for post-draft academic polishing.

This skill automates the multi-round research review process. It iteratively reviews provided work using advanced AI models (Codex MCP), identifying critical weaknesses, implementing fixes, and re-reviewing until the content achieves a positive assessment or the maximum round limit is reached. Ideal for refining complex academic papers, technical designs, or large codebases that require rigorous, iterative quality assurance.

This skill executes an autonomous, iterative research review loop, simulating a rigorous peer-review process. It repeatedly uses an external OpenAI-compatible LLM via API calls to score, critique, and identify weaknesses in a given research topic or document. The process continues to refine the content by implementing suggested fixes until the LLM provides a positive assessment or the maximum round limit is reached. Ideal for academic writing, technical documentation, and refining complex proposals.

This skill automates the iterative process of academic paper refinement, simulating the rigorous peer-review cycle of top-tier conferences (e.g., NeurIPS, ICML). It connects with an external LLM (MiniMax) to receive multi-round, critical feedback, tracks state persistence, and guides the user through necessary revisions until the research is deemed submission-ready. Ideal for maximizing the quality of technical writing.

Performs OWASP MASTG-aligned penetration testing on iOS and Android apps, combining binary static analysis, dynamic interception with Burp/Frida, and API/data storage reviews to uncover insecure storage, communication, or authentication flaws before release.

Structured facilitation of post-incident reviews that captures timelines, successes, failures, root causes, response metrics, and actionable improvements to strengthen future incident response.

Detects and analyzes fileless malware that resides only in memory via PowerShell, WMI, .NET reflection, registry payloads, and LOLBins, guiding LOLBin rule development, WMI persistence reviews, and memory/EDR triage.

Detects illicit OAuth consent grants in Azure AD / Microsoft Entra ID by enumerating OAuth2 permission grants, reviewing consent audit logs, analyzing permission scopes and publisher verification via Microsoft Graph, and generating risk reports for SOC analysts.

A step-by-step playbook for spotting and abusing JavaScript prototype pollution in both browsers and Node.js services to trigger DOM XSS, remote code execution, and authorization bypasses during security hunts and code reviews.

Extract, parse, and analyze Windows EVTX files with Chainsaw, Hayabusa, and EvtxECmd to hunt lateral movement, privilege escalation, and persistence artifacts during incident response and compliance reviews.

Internal Feishu/Lark notification utility that other skills call to push event cards or run interactive dialogs via webhook or bridge, ensuring safe fire-and-forget delivery whenever checkpoints, experiments, reviews, or pipelines change state.

This comprehensive, multi-phased workflow guides users from a broad research direction to validated, refined, and actionable ideas. It orchestrates literature searching, idea brainstorming, novelty verification, and critical review, resulting in a detailed idea report and an experiment plan for the top concept. Use this when starting a project from scratch.