task-router

Selects optimal execution strategies for tasks using a decision matrix with trigger conditions.

86|9|Updated Nov 12, 2025
One-click install
npx skills add https://github.com/arpitnath/super-claude-kit --skill task-router
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-router
Source: https://github.com/arpitnath/super-claude-kit/tree/main/skills/task-router
Command: npx skills add https://github.com/arpitnath/super-claude-kit --skill task-router

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude often has many tools and no clear guidance on when to delegate to sub-agents versus working directly. This Skill provides a decision matrix to consistently pick the optimal approach at task start or when unsure of the best path.

Core Features & Use Cases

  • Decision Matrix: Clear rules that map task characteristics to an optimal execution path (direct work, sub-agent delegation, or hybrid approaches).
  • Guided Invocation: Explicit how-to for invoking each chosen path (when to call agent-developer, Explore, architecture-explorer, etc.).
  • Use Case: Start a new project task and quickly decide whether to draft a plan, build a mini-agent, or explore the codebase.

Quick Start

Ask Claude: "What is the best approach to [task]?" and let Task Router provide a recommended path and concrete next steps.

Frequently Asked Questions about task-router

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I decide whether to delegate a task to a sub-agent or handle it directly?

Task Router applies a decision matrix that maps task characteristics—complexity, scope, codebase size, and approach certainty—to optimal execution paths: direct work, sub-agent delegation, or hybrid approaches. It provides explicit rules and concrete next steps for each choice.

What's the best way to plan a multi-file or large codebase change?

Task Router recommends delegating to specialized sub-agents like agent-developer or architecture-explorer based on task scope. For large codebases, it routes to codebase exploration first, then identifies the optimal execution strategy before implementation begins.

When should I use sub-agents like Explore, labs-specialist, or database-navigator instead of working directly?

Task Router triggers sub-agent delegation when tasks involve uncertain approaches, integration planning, architectural decisions, or specialized domains. It provides invocation instructions for each sub-agent and criteria for when direct work is more efficient.

How do I use Task Router at the start of a new project?

Ask Claude: 'What is the best approach to [task]?' Task Router analyzes task characteristics against its decision matrix and returns a recommended execution path—whether to draft a plan, build a mini-agent, explore the codebase, or proceed directly—with concrete next steps.

What task characteristics determine routing decisions?

Task Router evaluates complexity, scope, codebase size, approach certainty, and whether multi-file changes or integration planning is needed. These trigger conditions map to specific sub-agents or direct work, producing a clear plan with routing rationale.

Can Task Router help when I'm uncertain which execution strategy to use?

Yes. Task Router is designed for moments of uncertainty. It applies consistent decision rules to task characteristics and recommends the optimal path—whether delegation, hybrid collaboration, or direct execution—with explicit invocation instructions for your chosen route.