Skill UI

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.

AgentHub spawns parallel git worktree agents that compete on tasks, evaluates their outputs via metrics or LLM judges, and merges the top branch for optimizations, research, or content variations.

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 specialized downstream skill for CTF-sandbox workflows. Used to analyze complex security challenges driven by AI agent interactions, prompt injection, or infrastructure vulnerabilities. Focuses on tracing control chains involving untrusted input, tool side effects, deployment drift, container runtime issues, and CI/CD supply chain provenance. Ideal for rigorous vulnerability assessment in modern, distributed systems.

A specialized skill for advanced runtime analysis of Android applications, primarily used in CTF and security research. It covers techniques like hooking specific system boundaries (JNI, WebView), bypassing security measures (SSL pinning, root checks), and recovering sensitive data or request signatures. Ideal for deep inspection of app trust boundaries and complex mobile logic.

A specialized skill for analyzing client-side persistence mechanisms, including cookies, localStorage, sessionStorage, IndexedDB, and Service Workers. It is crucial for security testing and CTF environments where application behavior or critical decision branches are determined by stored session state, cached data, or local client-side variables. Use this to trace the smallest stateful sequence leading to a decisive outcome.

This skill specializes in analyzing built frontend artifacts, going beyond static source code. It reconstructs the dynamic JavaScript structure, tracks chunk loading paths, and interprets source maps and build manifests to recover hidden routes, APIs, and runtime behaviors. Essential for deep security analysis and understanding execution flow from deployed bundles.

A specialized downstream skill for complex CTF challenges, focusing on cryptographic analysis, steganography, and mobile system forensics. It guides the user through recovering complex data chains, such as decoding blobs, tracing cryptographic transforms (keys, IVs, nonces), inspecting hidden media payloads, and analyzing mobile trust boundaries (e.g., APK/IPA signing logic, local storage, SSL pinning). This skill is designed to be used only after a main sandbox orchestrator has established the operational context.

A specialized downstream skill for advanced CTF and security sandbox environments. This tool is used when the challenge requires reconstructing the exact message sequence, state transitions, and field mutations necessary for a system to accept a session. It handles complex tasks like recovering custom framing, checksum validation, stateful replay, and identifying the minimal conversation path that proves a specific branch acceptance.

This specialized skill traces the complete lifecycle of an uploaded or imported file through complex backend systems. It maps the sequence from ingress to final consumer, tracking every derived artifact, archive extraction, format conversion, parser invocation, and deserialization step. It is crucial for security analysis, vulnerability research, and understanding how a file reaches a decisive backend effect after initial sandbox assumptions are made.

A specialized skill for detecting discrepancies (drift) between declared API contracts (such as GraphQL schemas, OpenAPI specs, and RPC manifests) and the actual behavior of live backend handlers. It is used to identify hidden operations, contract mismatches, or vulnerabilities resulting from schema evolution, versioning skew, or implementation gaps. Must be used after initial sandbox assumptions are established.