Skill UI

This guide details the process of parsing Windows LNK shortcut files to extract crucial forensic artifacts. It gathers information such as target paths, MAC timestamps, volume serial numbers, and machine identifiers. This technique is invaluable in digital forensics, helping investigators reconstruct user activity timelines, track accessed files on removable media, or build comprehensive evidence from compromised systems.

Guides on using SwanLab for open-source ML experiment tracking, offering local or self-hosted dashboards, rich media logging, and integrations with PyTorch, Transformers, Lightning, or Fastai for comparing runs and monitoring metrics.

Guides fine-tuning and evaluation of OpenVLA-OFT/OFT+ for robot action generation, covering LoRA adaptation, continuous action heads, FiLM conditioning, and LIBERO/ALOHA benchmarks plus deployment considerations.

This guide implements a secure conduit architecture for Operational Technology (OT) remote access, adhering to IEC 62443 standards. It establishes a layered defense using DMZs, jump servers, and MFA gateways. Use it to secure third-party vendor access to SCADA/ICS equipment, replacing risky direct VPN connections and remediating audit findings on uncontrolled access.

Guides users through a structured 23-step interview to design, generate, and deploy Claude plugins across claude.ai and Claude Code, handling activation prompts, platform quirks, and GitHub pushes.

Soft Predict Future is a structured foresight engine that triggers whenever the user asks about future outcomes or scenarios. It enforces a nine-step analytical pipeline (validation, signal collection, scoring, driver extraction, etc.), highlights required searches and inputs, and directs the user to web-enabled reasoning for predictive analysis.

Guides analysts through soft-mode startup screening by extracting company profiles, scoring eight VC dimensions, applying four investor lenses, and delivering a PASS/DECLINE verdict with a concise memo.

The /hub:spawn command launches N subagents that work on the same task simultaneously. Each agent operates within an isolated git worktree, ensuring true parallelism and resource separation. Users can optionally specify templates (e.g., `optimizer`, `refactorer`) to guide agents toward specific strategies for improving code quality, performance, or test coverage. Ideal for complex software engineering tasks requiring diverse, competing approaches.

A structured framework for performing initial security incident triage. It guides analysts through classifying incident types using established standards like NIST SP 800-61r3, assigning business impact severity (P1-P4), enriching alerts with threat intelligence, and determining containment and escalation paths. Use when SIEM/EDR alerts require human judgment or when coordinating multiple concurrent security events.

Automatically analyzes unfamiliar codebases to generate a comprehensive, structured onboarding guide. It systematically detects package manifests, framework fingerprints, architecture maps, key entry points, and coding conventions. Ideal for new developers joining a project or setting up a repository for the first time.

A comprehensive guide covering best practices for building and debugging Nuxt 4 applications. It details patterns for ensuring hydration safety, optimizing data fetching with `useFetch` and `useAsyncData`, managing complex routing rules, and implementing lazy loading for superior performance across SSR and client-side environments.

This skill provides guidance on implementing common architectural patterns and best practices within the PyTorch framework. It is designed for developers building sophisticated deep learning models, helping to improve structure, efficiency, and code maintainability when working with neural networks.