MCP App StoreMCP App Store
from harness-creator10
Generates a sophisticated .claude/ harness framework using Fusion Architecture to orchestrate multi-agent development workflows.
This skill enables an agent to scaffold a complete AI-assisted development environment (a 'harness') within a project's .claude/ directory. It implements a 'Fusion Architecture' based on GAN-inspired principles, separating the planning, generation, and evaluation phases to ensure higher quality output and objective grading of implementation.
Use this skill when a user wants to set up a new AI development structure, scaffold a fresh project from 0 to 1, or add formal agent orchestration to an existing codebase. It is particularly useful for complex projects requiring domain-specific specialists.
Designed specifically for Claude Code and other agents supporting the .claude/ directory convention and sub-agent spawning capabilities.
This skill has not been reviewed by our automated audit pipeline yet.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
mog — Microsoft Ops Gadget
Command-line toolkit for Microsoft 365 (Mail, Calendar, OneDrive, Contacts, Tasks, Word, PowerPoint, Excel, OneNote) with slug and multi-account support.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Build Unplanned Feature
Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo
AI Pair Collaboration
Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate
Box0 (b0)
Run and coordinate parallel AI sub-agents locally or on a server to delegate reviews, tests, research, and other specialist tasks.