consulting-design
Consult Gemini AI for architecture alternatives, design trade-offs, and brainstorming. Use when seeking different perspectives on design, evaluating architectural approaches, comparing solutions, or generating creative ideas.
Works with
---
name: consulting-design
description: Consult Gemini AI for architecture alternatives, design trade-offs, and brainstorming. Use when seeking different perspectives on design, evaluating architectural approaches, comparing solutions, or generating creative ideas.
license: MIT
---
# Design Consultation with Gemini
## Tools
| Tool | Use For |
| ------------------------- | ------------------------------------------- |
| `mcp__gemini__ask-gemini` | Architecture, design review, trade-offs |
| `mcp__gemini__brainstorm` | Generating alternatives, creative solutions |
## ask-gemini
```json
{
"prompt": "I'm designing [system]. Current approach: [desc]. Trade-offs and alternatives?",
"model": "gemini-2.5-pro"
}
```
Options: `changeMode: true` for structured edits, `sandbox: true` for code execution
## brainstorm
```json
{
"prompt": "How might we [challenge]?",
"domain": "software",
"methodology": "auto",
"ideaCount": 10
}
```
Methodologies: `divergent`, `convergent`, `scamper`, `design-thinking`, `lateral`, `auto`
---
## Gotchas
- **Gemini brainstorm output is non-deterministic** — same prompt rerun gives different ideas; save outputs you want to reference.
- **`ask-gemini` doesn't preserve conversation context across calls** — multi-turn questions need explicit history concatenation in each prompt.
- **API quota is per-project per-day** — bursting on a free tier locks the project out until midnight Pacific.
- **Output is markdown but can include LaTeX math** — downstream tooling that doesn't render math gets garbled output without warning.
- **`brainstorm` defaults to 5 ideas** — for divergent ideation, explicitly request more; the default is a hard cap.More Testing skills
tdd
mattpocock/skills
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
setup-pre-commit
mattpocock/skills
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

