Skill UI

This advanced skill details dual-use security techniques for analyzing protected binaries, conducting malware analysis, and performing authorized penetration testing. It strictly mandates that users confirm explicit written authorization, adhere to defined scope, and ensure legal compliance (e.g., CFAA, DMCA). Use cases include CTF competitions, academic research, and internal security auditing, emphasizing defensive recommendations and evidence preservation.

This advanced skill details dual-use security techniques for analyzing protected binaries, conducting malware analysis, and performing authorized penetration testing. It strictly mandates that users confirm explicit written authorization, adhere to defined scope, and ensure legal compliance (e.g., CFAA, DMCA). Use cases include CTF competitions, academic research, and internal security auditing, emphasizing defensive recommendations and evidence preservation.

Provides comprehensive frameworks and best practices for conducting thorough competitive landscape analysis. This skill helps users systematically analyze market competition, identify potential market gaps, pinpoint differentiation opportunities, and develop robust, winning market positioning strategies to secure a sustainable competitive advantage.

Use this command to set up a structured multi-agent collaboration environment within AgentHub. It allows you to define the core task, specify the required number of agents, and configure detailed evaluation criteria (metrics, directions, and commands) for both quantitative benchmarking and qualitative LLM judging. This is the starting point for any agent competition or complex AI workflow.

This command executes the entire AgentHub lifecycle in a single, chained invocation. It automates complex development tasks by sequentially handling initialization, capturing performance baselines, spawning multiple specialized agents, evaluating the results (via metrics or LLM judging), and finally presenting a winner for merging. Use this when running an end-to-end competition or complex refactoring task.

Spawns multiple AI agents in isolated git worktrees to compete on the same task, then ranks results by metrics or LLM judge and merges the winning branch.

This system treats ideas like living species on an 'evolution island.' Instead of simple storage, it runs structured, multi-round iterations simulating biological processes: competition, crossbreeding, and mutation. Users input initial concepts, and the tool systematically evaluates them using a 6-dimensional scoring framework (Novelty, Feasibility, Value, etc.). It helps users deepen viability, discover unexpected connections between disparate ideas, and prioritize the most robust concepts for development and investment.

A speed-optimized, comprehensive checklist for rapid security assessments. This guide covers full-cycle penetration testing methodologies, including deep reconnaissance (WAF bypass, CDN mapping), access control testing (MFA, JWT, API keys), and session management vulnerabilities. Ideal for time-boxed engagements, CTF competition, or initial service triage.

A comprehensive playbook detailing identification and bypass techniques for major binary protections, including ASLR, PIE, NX/DEP, RELRO, and stack canaries. This guide is essential for understanding how to exploit modern, difficult-to-break systems in advanced security research and CTF competitions.

Creates and maintains a product marketing context document capturing positioning, audience, personas, pain points, competition, brand voice, and proof points for consistent marketing work.

This specialized skill provides comprehensive guidance for authors targeting the journal Industrial Economics Research. It covers the journal's positioning, preferred research topics (e.g., industrial organization, competition policy, digital transformation), required academic structure (introduction, literature review), and common pitfalls to avoid. It helps authors tailor their manuscripts to meet the high standards of CSSCI-level academic publishing.

This comprehensive guide helps authors determine if their robotics manuscript is suitable for the RoboCup Symposium. It provides specialized advice on conference positioning, required evidence (e.g., league performance, benchmarks), and framing for competitive robotics domains like robot soccer, rescue, and service robots. It emphasizes grounding the contribution in empirical, competition-based evidence rather than general theoretical work, serving as a fit and re-framing tool for high-level CI/AI submissions.