Advisor Skills for Claude Code
A set of advisor skills for consulting specialized models during complex engineering work.
Advisor Skills extends Claude Code’s capabilities by giving it the ability to consult specialized external models and agents. Just as senior engineers seek second opinions or research documentation when stuck, this toolset allows Claude to break tunnel vision, verify information, and deepen reasoning.
What This Plugin Does
-
Break Tunnel Vision: Use the Strategist agent to get an unbiased, high-level perspective on architectural decisions. By delegating complex reasoning to a specialized sub-agent (using the Opus model), you save costs by reserving high-intelligence processing only for critical strategic decisions.
-
Verify & Research: Use Gemini to fetch real-time documentation and libraries, preventing hallucinations about outdated APIs.
-
Deepen Reasoning: Use Codex to handle complex algorithmic logic and multi-step reasoning tasks that require dedicated focus.
Instead of relying on a single model’s training data, this workflow enables a collaborative AI approach to problem-solving.
Installation
/plugin marketplace add qduc/advisor-skills
Skills
Consult
Seek second opinions from specialized AI models and agents:
- Strategist Agent: Unbiased, objective advice on complex strategic decisions and architectural trade-offs
- Codex: Deep reasoning for complex logical problems and multi-faceted analysis
- Gemini: Online research for current information, documentation, and real-world examples
Use when stuck on difficult problems, validating approaches, or needing fresh perspectives.
Installation:
/skill install consult
Strategist Cooperation
Guidelines for effective collaboration with the Strategist agent, including patterns for session continuity, preparing context, and handling advice.
Installation:
/skill install strategist-cooperation
Agents
Strategist
A specialized agent that provides an outsider’s perspective on difficult problems without being influenced by existing code, implementation details, or project constraints.
Key capabilities:
- Radical objectivity - evaluates everything purely on merit
- Fresh perspective - unencumbered by technical debt or sunk costs
- Strategic thinking - focuses on fundamental principles
- Devil’s advocate - challenges assumptions and explores alternatives
Use when:
- Stuck on architectural decisions and going in circles
- Team debates with strong conflicting opinions
- Need to cut through bias and see the situation with fresh eyes
- Evaluating major refactoring or rewrite decisions
The agent applies first principles thinking, identifies hidden assumptions, and provides decision frameworks rather than prescriptive solutions.
Why This Approach?
This “Council of Experts” methodology provides:
- Cost Efficiency: Use lighter models for main work, consult expensive models only for critical decisions
- Reduced Hallucination: Cross-reference information across multiple sources
- Better Decision Making: Get multiple perspectives before committing to major changes
- Specialized Expertise: Leverage models optimized for specific tasks
Check out the GitHub repository for detailed documentation and contribution guidelines.