Skill UI

This CLI alias executes a comprehensive teardown protocol for PUA agents, designed for development environments. It safely releases all active agent and loop states, ensuring a clean system reset. It automatically manages configuration files like ~/.pua/config.json, preserving unknown fields while providing reliable, evidence-based cleanup.

A comprehensive skill for integrating X (Twitter) data into applications, scripts, data pipelines, and AI agents. It supports advanced scraping tasks including tweet searching, user lookup, following export, and media downloading. Functionality is exposed via generated SDKs (Python, TypeScript, Go, etc.), REST endpoints, signed webhooks, and the MCP server for agent automation.

Design a persistent multi-agent operating system on Claude Code with kernel routing, specialist agents, slash commands, file-based memory, and scheduled automation for long-lived projects.

This guide helps users navigate and understand the complex components of the ECC (Everything Claude Code) ecosystem, including skills, commands, agents, hooks, and rules. It provides structured paths for new user onboarding, feature discovery, installation planning, and troubleshooting, ensuring answers are derived from the current repository state.

The Ejentum Reasoning Harness is a comprehensive library of cognitive operations designed to guide complex AI agents through critical thinking tasks. It exposes four specialized harnesses (reasoning, code, anti-deception, memory) that mitigate common failure modes like hallucination and reasoning decay. Instead of a fixed answer, the agent ingests a detailed, executable scaffold—including failure patterns, procedures, and falsification tests—to ensure robust, self-verified output.

The Founder-Mode Executive Team simulates a complete C-suite of 13 specialized agents (CFO, CMO, CPO, etc.) and provides 21 structured slash commands. It is designed for founders and executives who need multi-perspective analysis, deep strategic reviews (e.g., unit economics, threat modeling), consensus building, and structured decision logging. Use it when orchestrating complex, multi-phase business decisions.

A structured founder interview designed to gather the canonical, comprehensive data for a company, including financials, team structure, business metrics, and strategic risks. It generates a single, authoritative `company-context.md` file, serving as the single source of truth for all subsequent AI agents and strategic decision-making processes. Essential for initial setup or after major company life events like funding rounds or pivots.

Expert skill for building Model Context Protocol (MCP) servers and tools from scratch. Covers the full development lifecycle—from defining tool schemas and resources to implementation, testing, and publishing to registries. Supports robust patterns using TypeScript and Python for integrating custom capabilities into AI agents.

This is a comprehensive lookup reference for the Mercury MCP server tools. It guides AI agents on how to interact with a virtual team workspace, enabling structured communication for messaging teammates, managing threads and tasks, scheduling complex automations, and performing administrative graph edits. Use this when your agent needs to execute specific team workflows.

Bilig WorkPaper provides a code-first runtime environment for complex spreadsheet business logic. It allows agents to interact with structured data using formulas and JSON workbooks via deterministic API calls (MCP/TypeScript). This is ideal for replacing unreliable UI automation in use cases like quote calculators, budget modeling, and data validation, ensuring calculation integrity through explicit read-back proof.

This advanced skill manages complex, large-scale development tasks by coordinating multiple, specialized subagents in parallel. It systematically decomposes the goal into isolated missions, manages resource quotas (token usage), and handles error recovery across multiple files and components. Ideal for large feature builds, system refactoring, or complex applications requiring multiple, concurrent roles (Planner, Builder, Tester).

This technical skill is designed to verify the compatibility of the Codex CLI with skills compiled from MDA source. Loading this skill confirms that the CLI loader successfully parses the SKILL.md format, adhering to the agentskills.io v1 envelope subset. It is primarily used for testing build pipelines, metadata integrity, and ensuring robust compatibility between MDA compilation and runtime ingestion.