MCP App StoreMCP App Store
from skill-router19
A meta-skill that indexes installed skills and routes substantive requests to the most relevant one via suggest or auto mode.
Skill Router acts as a dispatcher for other agent skills. It scans the local skill directory, builds a lightweight in-session index, and then determines if a user request is a substantive task that would benefit from a specific installed skill.
Activate this at the start of a session when you have multiple specialized skills installed and want to ensure the most appropriate one is used for complex tasks without manual selection for every turn.
Specifically designed for Claude Code and other agents supporting local file system access and bash execution.
Skill Router is a pure-instruction skill that guides agents on when to route requests to other skills vs executing directly. No scripts included — entirely declarative SKILL.md with clear trigger boundaries, a 5-step decision path, and concise output shapes. Clean security profile with no executable code. Architecture follows skill spec conventions with references/ directory and progressive disclosure. Niche usefulness — overlaps with built-in agent skill-matching logic.
Clean skill with no security concerns. Duplicate last paragraph in SKILL.md body (likely copy-paste artifact). Skill is well-structured but its value proposition is narrow — most agent runtimes already handle skill routing internally.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
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.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
tmux Remote Control
Control tmux sessions for interactive TTYs: send keystrokes, capture panes, orchestrate parallel coding agents, and monitor output safely.