Skill UI

This comprehensive skill acts as a virtual Chief of Staff, guiding founders through a rigorous 12-phase interview process. It systematically gathers and structures every facet of a business—from foundation and strategy to legal and governance—into a compliant Open Knowledge Format (OKF) bundle. Ideal for creating comprehensive, machine-readable company documentation, internal wikis, or knowledge bases for AI agents.

Automatically analyzes complex AI operations, including token usage patterns, model tier suitability, cache hit rates, and agent redundancy. It identifies potential waste and provides actionable, prioritized recommendations with estimated dollar savings to significantly reduce operational costs and improve efficiency across LLM pipelines.

This tool generates a detailed cost report, tracking token usage and associated USD costs across all AI agents and models. It provides crucial insights into budget utilization, breaking down spending by model (e.g., Opus, Sonnet), agent, and operational tier (Tier 1/2/3), helping teams manage spending and optimize resource allocation.

This skill runs a single, simulated tick of a defined business pod (Sales). It is designed for dry-run testing, allowing users to validate inputs, resolve agents, and reserve budgeted resources without invoking real LLM workers. It handles template loading, schema validation, budget management, and emits structured status reports for subsequent workflow consumption.

An interactive tool designed to discover, select, and assemble specialized teams of AI agents. It supports structured agent collections across different domains (e.g., Engineering, Marketing). Users select multiple roles for a specific task, and the skill launches them in parallel, synthesizing their independent findings into a unified report, including consensus and conflict analysis.

This utility allows agents or desks to emit structured signals (e.g., hands-up, blocked, done, checkpoint) in JSON format. These signals are crucial for real-time dashboard consumption, providing the operator or coordinator with immediate, actionable insights into the work status, disagreement points, or required attention levels of various work units. It also supports optional 'outcome signals' for self-assessment calibration.

This protocol simulates a diverse, anonymous jury of 3 to 5 specialized subagents to reach a committed, non-ambiguous verdict. It is designed to combat cognitive biases like anchoring and groupthink by running blind, independent opinions before structured deliberation. Ideal for high-stakes decisions across product development, architecture, strategy, and vendor choice where a single perspective is insufficient.

Creates an Agent Authority Charter to define permissions, delegation, approvals, escalation, and audit requirements for AI agents before enterprise or regulated deployment. Helps legal, compliance, risk, and product teams document what an agent may and may not do, prepare for human review, and ensure auditable governance across the agent lifecycle.

This skill provides a comprehensive audit framework for evaluating AI agents used in legal, compliance, or business operations. It assesses the risks associated with delegated authority—such as sending messages, filing documents, or making payments—by checking for adequate controls, logging, revocation mechanisms, and clear accountability chains. It is essential for firms connecting agents to sensitive systems like CRM, court portals, or financial accounts to ensure safe and compliant deployment.

This skill determines if an AI agent's proposed action, output, or recommendation remains compliant and admissible for execution or institutional reliance at runtime. Unlike static authorization, it assesses current conditions—such as changed policies, expired authority, or new risks—to ensure that any consequential action taken by an agent or relied upon by an institution is valid and permissible right now.