From consultant
Ask a specific AI model (codex, gemini, grok, perplexity, claude) for focused analysis or a second opinion
How this skill is triggered — by the user, by Claude, or both
Slash command
/consultant:consultThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Ask a specific AI model for focused analysis or a second opinion.
Ask a specific AI model for focused analysis or a second opinion.
/consultant:consult codex What's the best approach for this architecture?
/consultant:consult gemini Analyze this code pattern
/consultant:consult grok What do you think about this design?
/consultant:consult perplexity Research latest React trends
/consultant:consult claude Search for best practices on error handling
| Model | Agent | Specialization |
|---|---|---|
| codex / gpt5 | codex-researcher | Advanced reasoning, technical analysis, complex problem-solving |
| gemini | gemini-researcher | Multi-perspective analysis, creative solutions |
| grok | grok-researcher | Alternative LLM perspective, latest Grok-4 model |
| perplexity | perplexity-researcher | Web research with citations, real-time data |
| claude | claude-researcher | Web research, detailed synthesis |
Parse $ARGUMENTS to extract:
Launch ONE agent using the Task tool:
Task tool with subagent_type: consultant:[model]-researcher
Map model names:
codex or gpt5 → consultant:codex-researchergemini → consultant:gemini-researchergrok → consultant:grok-researcherperplexity → consultant:perplexity-researcherclaude → consultant:claude-researcherIf no model specified or model not recognized, ask the user which consultant they want.
npx claudepluginhub tinetti/claude-plugins --plugin consultantGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Implements work from a spec or tickets using TDD at agreed seams, with regular typechecking and test runs, followed by code review.