Skill UI

A comprehensive guide for engineering teams to manage critical incidents related to Clerk authentication and SaaS platform outages. It covers full incident lifecycle procedures, including initial triage, emergency auth bypass implementation, key rotation, session recovery scripts, and post-incident root cause analysis. Use this when facing production authentication failures or security breaches.

This skill enables the coordination of multiple specialized AI agents within a single session. It is designed for complex, multi-domain tasks such as comprehensive code reviews, security audits, or full-stack feature implementations. It coordinates expertise across various domains (backend, frontend, testing, architecture) to provide holistic analysis and actionable recommendations.

This skill provides a structured approach to systematically identify security threats by applying the STRIDE methodology (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege). It is crucial for conducting thorough threat modeling sessions, analyzing system architectures, reviewing security design decisions, and creating robust security documentation for compliance and auditing purposes.

Provides guidance for organizing and navigating Jupyter Notebook workflows, focusing on structuring analysis, experiments, and reports within interactive Python sessions.

A forensic tool for performing post-mortem analysis on AI-assisted coding sessions. It goes beyond simply stating what was done, determining *why* work deviated (e.g., spec ambiguity, repo friction, agent error), identifying scope creep, and classifying rework patterns. It provides evidence-backed recommendations to improve prompts, codebase health, and future development workflows.

This comprehensive guide details the multi-step workflow for responding to sophisticated phishing incidents. It covers everything from initial triage and detailed email header analysis to analyzing malicious URLs and attachments in sandboxes. Key steps include determining the scope of impact, implementing immediate containment actions (like purging emails and revoking sessions), and executing thorough remediation to neutralize the threat and recover affected accounts.

The Desktop Commander MCP grants agents deep reach across the user's entire operating environment, extending far beyond the typical IDE sandbox. Key capabilities include maintaining persistent shell sessions, managing long-running background processes, accessing arbitrary filesystems, and natively handling structured data formats (Excel, PDF, DOCX). It also enables remote operations via SSH and large-scale content search, making it ideal for complex, multi-turn development, DevOps, and data analysis workflows.

Opens a named, traced browser session bound to an RVF cognitive container, recording every action as a ruvector trajectory step for later replay, analysis, and reuse by downstream browser skills.

This tool restores project context, crucial after a session clear. It comprehensively analyzes Git history, summarizing recent commits, tracking uncommitted changes, scanning for outstanding TODOs/FIXMEs, and verifying the current project structure. It helps developers quickly re-establish the full working context to resume work efficiently.

A specialized, downstream skill designed for forensic analysis within a confined sandbox environment, particularly for CTF challenges. It guides the user to inspect the full stack behavior, including API interactions, server routing, browser state (cookies, local storage), and asynchronous worker processes. Use this skill to trace complex, end-to-end request flows, debug authentication/session leaks, or diagnose discrepancies between frontend UI and backend enforcement.

Analyze AI-assisted coding sessions to identify root causes, scope drift, and rework patterns. Generates detailed reports explaining what happened, why it happened, and actionable recommendations for improving future prompts and workflows. Essential for postmortems on AI coding sessions.

This skill enables running the Pi agent non-interactively for repository analysis and implementation tasks. It involves setting the Bash working directory, checking Pi availability, and executing sessionless tasks using JSON mode. Users should delegate analysis or implementation to Pi by passing prompts as quoted arguments. Security measures include limiting tool access and avoiding credential handling.