Skill UI

Runs a multi-persona dev team session where PM, Architect, Developer, and QA each respond to a topic from their own role. Use for feature design, proposal review, or initiative onboarding when you want multi-role perspectives without switching agents.

A comprehensive, stack-agnostic tool for deeply evaluating agent harnesses. It checks for broken code paths, redundant instructions, and the overall usefulness of agent logic using a structured, multi-stage dual-judge protocol. The process involves high-priority questionnaires (Q1, Q2) before running three defined tracks: A (Correctness), B (Redundancy), and C (Usefulness). Ideal for auditing complex agent systems before deployment or major refactoring.

This tool initializes a dedicated AgentHub session for multi-agent collaborations. It requires defining the core task, specifying the number of parallel agents, and configuring detailed evaluation criteria (including the evaluation command, target metric, and measurement direction). Upon execution, it generates a unique session ID and prepares the entire environment for subsequent agent spawning and competitive evaluation, optionally capturing a performance baseline.

Monitor the real-time progress and overall state of an AgentHub session. This tool displays detailed information including agent branch activity, commit counts, frontier status, and recent board updates, allowing users to effectively track complex multi-agent workflow execution.

An advanced, automated pipeline designed for comprehensive, deep-dive Open Source Intelligence (OSINT) gathering and reconnaissance against authorized domains. It executes the full methodology—from passive data harvesting and subdomain discovery to multi-agent content fan-out, vulnerability identification (BOLA/IDOR), and automated findings generation. The output is a single, consolidated, multi-tab deliverable (XLSX), eliminating the need for manual follow-up or superficial reporting.

This comprehensive wizard guides users through setting up various AI agent clients (e.g., Claude Code, Codex, CodeBuddy) to connect with a Memory Proxy. It handles configuration scanning, gathering necessary credentials (Proxy URL, User Key), selecting the specific agent, and validating connectivity via live API health checks for multiple protocols (Anthropic, OpenAI, etc.) before writing the final configuration.

This skill automates the final deployment phase of an agent system. It converts a validated build sheet into four ordered JSON payloads (environment, agent, session, kickoff) and generates a resumable `launch.sh` script. Crucially, this process enforces API-key safety by requiring the user to run the script in their shell, pulling the Anthropic API key from the environment variable, thus ensuring the key never appears in logs or files. It provides a structured, multi-step launch sequence.

Multi-agent decision swarm that activates 20 legendary Tianya forum experts in parallel for a user objective. A coordinator assigns the task, each expert provides specialized insights, and a synthesis agent merges consensus and disagreements into a structured report with risks, recommendations and action plans.

Tinte is an agent-native infrastructure designed for generating, compiling, and managing consistent design systems from a single source of truth. It maintains a graph of 13 semantic OKLCH color tokens, compiling them into multiple formats including shadcn/ui presets, VS Code themes, and terminal configurations. Use it to ensure brand consistency, extract themes from images (via AI), and generate code previews with professional styling.

This agent is dedicated to systematically exploring technical ideas, such as new features, refactoring, or bug fixes, *before* committing to code changes. It investigates the existing codebase, analyzes current architecture, compares multiple potential approaches (including pros, cons, and effort), and generates a structured 'exploration' report with a clear recommendation and identified risks. It ensures thorough planning and risk mitigation during the design phase.

Manage multiple local CLI agents via tmux sessions including starting, stopping, monitoring, and assigning tasks within an explicitly authorized workspace. This skill enables parallel execution, log tailing, and task assignment for automated workflows. Requires tmux and python3 installation. Use for orchestrating local agent infrastructure and verifying task completion without automatic scheduling.

Optimize multi-agent systems through coordinated profiling, workload distribution, and cost-aware orchestration. This skill helps improve agent performance, throughput, and reliability by identifying bottlenecks in workflows. It covers context window optimization, parallel execution strategies, and cost management for LLM usage. Suitable for engineering complex AI workflows requiring high efficiency and stability.