Stats
Actions
Tags
From consultant
Multi-model AI consultation and research using cursor-agent. Supports CONSULTATION (single query to specific model), RESEARCH (parallel multi-agent queries), and DELIBERATION (multi-round debate). Use when user says 'ask gpt', 'ask opus', 'consult gemini', 'do research on', 'deliberate on', or wants second opinions from AI models.
How this skill is triggered — by the user, by Claude, or both
Slash command
/consultant:consulting-modelsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Multi-model consultation using cursor-agent CLI.
Multi-model consultation using cursor-agent CLI.
Ask a specific AI model for focused analysis.
Triggers: "Ask [model] about", "Consult [model] on", "What does [model] think"
Models: gpt, opus, gemini
Execute:
scripts/consult.sh "MODEL" "PROMPT"
Replace MODEL with alias, PROMPT with question. Output goes to stdout.
Launch multiple agents for comprehensive coverage.
Triggers: "Do research on", "Quick research:", "Extensive research on"
Intensities:
Execute:
scripts/research.sh "TOPIC" INTENSITY OUTPUT_DIR
scripts/collect.sh OUTPUT_DIR
See references/research-workflow.md for full workflow.
Agents critique each other and refine positions over 4 rounds.
Triggers: "Deliberate on", "Have models debate", "Peer review:"
See references/deliberation-workflow.md for full protocol.
# Single consultation
scripts/consult.sh "gpt" "What's the best rate limiting approach?"
# Parallel research
scripts/research.sh "API authentication" standard ./scratch/research
scripts/collect.sh ./scratch/research
| Model | Best For |
|---|---|
| gpt | Complex reasoning, technical analysis |
| opus | Code-focused, high reasoning |
| gemini | Multi-perspective analysis |
Full details: references/models.md
After collecting results:
Template: references/synthesis-template.md
npx claudepluginhub denisraison/claude-plugins --plugin consultantOrchestrates parallel analysis of coding problems across AI models (Claude, GPT, Gemini, Grok) via CLI tools or APIs, collects recommendations, and synthesizes optimal solution.
Runs 3 AI models in parallel (gpt-5.2-pro, gemini-3-pro-preview, claude-opus-4-5-20251101) for diverse perspectives on code queries. Invoke via /ask-council or auto-activates.
Queries AI models via OpenRouter, Gemini, or OpenAI APIs for second opinions on code, architecture, strategy, or prompting. Supports consensus, single opinion, and devil's advocate modes.