home / skills / zpankz / mcp-skillset / think-router

think-router skill

safe

This skill unifies reasoning, research, and analysis to streamline cognitive tasks across codebases and security and performance reviews.

npx playbooks add skill zpankz/mcp-skillset --skill think-router

Review the files below or copy the command above to add this skill to your agents.

Files (2)

SKILL.md

2.2 KB

---
name: think-router
description: |
  Unified router for reasoning, research, and analysis tasks.
  Consolidates reasoning-router + research-router + analysis-router.
---

# Think Router (Unified)

**Consolidates**: reasoning-router + research-router + analysis-router
**Purpose**: All analytical/cognitive tasks

## Triggers
```yaml
patterns:
  - analyze, debug, troubleshoot, audit
  - reason, think, prove, verify
  - research, investigate, deep-dive, study
  - security, performance, optimization
```

## Thinking Modes

### Analysis Mode
```yaml
triggers: [analyze, debug, troubleshoot, audit, security, performance]
agent: oracle
workflows:
  - Root cause analysis
  - Security audit
  - Performance profiling
  - Code review

sc_commands:
  - sc:analyze → Codebase analysis
  - sc:troubleshoot → Systematic debugging
```

### Research Mode
```yaml
triggers: [research, investigate, deep-dive, study, learn]
agent: researcher
skills:
  - deep-research (db/skill-db) - 7-phase methodology
  - codebase-researcher (db/skill-db) - Systematic codebase analysis
workflows:
  - Classify → Scope → Hypothesize → Plan → Query → Triangulate → Synthesize
```

### Reasoning Mode
```yaml
triggers: [reason, think, prove, verify, logic]
skills:
  - hierarchical-reasoning (db/skill-db) - Strategic/Tactical/Operational
  - think (db/skill-db) - ThoughtBox + mental models
  - reason (db/skill-db) - Parse → Branch → Reduce → Ground → Emit

patterns:
  - Forward thinking (goal → actions)
  - Backward thinking (goal ← requirements)
  - Branching (explore alternatives)
  - First principles (fundamental truths)
  - Meta-reflection (reasoning about reasoning)
```

## Integration with Skills
```yaml
unified_skills:
  deep-research:
    core: 7-phase research methodology
    extensions: codebase analysis, web extraction

  hierarchical-reasoning:
    core: 3-level cognitive architecture
    extensions: ThoughtBox patterns, mental models
```

## References
- Original reasoning-router: ~/.claude/db/skills/routers/reasoning-router/
- Original research-router: ~/.claude/db/skills/routers/research-router/
- Original analysis-router: ~/.claude/db/skills/routers/analysis-router/

Overview

This skill is a unified router for reasoning, research, and analysis tasks that consolidates reasoning-router, research-router, and analysis-router capabilities. It routes cognitive jobs into specialized thinking modes—Analysis, Research, and Reasoning—so complex investigative or decision problems are handled with structured workflows. The skill is designed to coordinate agent roles, workflows, and targeted sub-skills for systematic, repeatable outcomes.

How this skill works

The router detects intent from trigger patterns (e.g., analyze, research, reason) and selects an appropriate mode and agent profile (oracle for analysis, researcher for research, reasoning modules for logic). Each mode maps to workflows and sub-skills: Analysis for audits and debugging, Research for deep multi-phase inquiry, and Reasoning for structured argumentation and problem decomposition. It orchestrates methods like root cause analysis, 7-phase research, and hierarchical reasoning to produce actionable findings.

When to use it

When you need a repeatable process to debug, audit, or profile systems
When conducting deep, multi-source research or evidence triangulation
When solving problems that require formal reasoning or proof
When you want to combine codebase inspection with domain research
When choosing an investigative strategy (forward, backward, branching, first-principles)

Best practices

Start by providing clear triggers or goals so the router picks the right mode
Supply context (code, logs, hypotheses, data sources) to enable targeted workflows
Use the Research mode for structured inquiries using the 7-phase methodology
Use Analysis mode for security, performance, and root cause tasks with oracle agent
Break large problems into sub-tasks so hierarchical-reasoning can apply tactical and operational steps

Example use cases

Perform a security audit that combines code review, dependency checks, and threat modeling
Investigate a production outage: gather logs, hypothesize causes, run systematic troubleshooting
Execute a literature and codebase study to validate a technical design decision
Reason about trade-offs with forward and backward thinking to generate a roadmap
Triangulate conflicting data sources to synthesize confident recommendations

FAQ

How does the router choose a mode?

It matches input triggers and goals to predefined patterns and selects the agent and workflows mapped to the best-fit mode.

Can I combine modes for a single task?

Yes. The router supports hybrid flows where research informs analysis and reasoning structures the final synthesis.