cmd/sgai/skel/.sgai/skills/product-design/brainstorming/SKILL.md
Interactive idea refinement using Socratic method to develop fully-formed designs. When your human partner says "I've got an idea", "Let's make/build/create", "I want to implement/add", "What if we". When starting design for complex feature. Before writing implementation plans. When idea needs refinement and exploration. ACTIVATE THIS AUTOMATICALLY when your human partner describes a feature or project idea - don't wait for /brainstorm command.
npx skillsauth add sandgardenhq/sgai brainstormingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Transform rough ideas into fully-formed designs through structured questioning and alternative exploration.
Core principle: Ask questions to understand, explore alternatives, present design incrementally for validation.
Announce at start: "I'm using the Brainstorming skill to refine your idea into a design."
IMPORTANT: Hand the control back to the human partner so they can feed you with information.
IMPORTANT: Hand the control back to the human partner so they can feed you with information.
IMPORTANT: Hand the control back to the human partner so they can feed you with information.
After design is agreed upon, gather validation criteria for project-critic-council.
Ask these questions (each with escape hatch option):
Example:
sgai_ask_user_question({
questions: [{
question: "**Phase 4: Validation Criteria**\n\nHow will you know this feature is complete? What's the acceptance criteria?",
choices: [
"Tests pass and feature works as described",
"I'll define specific criteria (describe in Other)",
"Skip detailed validation - proceed with current understanding"
],
multiSelect: false
}]
})
IMPORTANT: Always include "Skip detailed validation" option to let users shorten the interview.
Log all validation criteria in @.sgai/PROJECT_MANAGEMENT.md under a ## Validation Criteria section.
IMPORTANT: Hand the control back to the human partner so they can feed you with information.
You can and should go backward when:
Don't force forward linearly when going backward would give better results.
During exploration:
Before proposing changes to existing code:
sgai_ask_user_question tool to ask structured questions. Example:
sgai_ask_user_question({
questions: [{
question: "Which approach do you prefer?",
choices: ["Approach A", "Approach B", "Need more details"],
multiSelect: false
}]
})
sgai_ask_user_question({
questions: [
{question: "Which database?", choices: ["PostgreSQL", "MySQL", "SQLite"], multiSelect: false},
{question: "Which features to include?", choices: ["Auth", "Logging", "Metrics"], multiSelect: true}
]
})
When asking questions during brainstorming, you MUST follow this protocol to ensure the human partner sees the full context:
Log to .sgai/PROJECT_MANAGEMENT.md FIRST:
Embed context IN the question field:
question parameter in sgai_ask_user_question MUST include the full context"Which database?""**Phase 1: Understanding**\n\nI need to understand your data persistence needs to design the architecture.\n\nWhich database do you prefer?"Terminal output continues as normal (this already works)
documentation
Start, stop, and steer agentic sessions in sgai workspaces. Use when you need to launch AI agent sessions, halt running sessions, or inject steering instructions to guide the agent mid-execution without stopping it.
development
Monitor sgai workspace status, events, progress, diffs, and workflow diagrams. Use when you need to observe what agents are doing, track progress, get the current state of all workspaces, subscribe to real-time updates via SSE, or inspect code changes.
development
Access agents, skills, and code snippets available in sgai workspaces. Use when you need to discover what agents are defined in a workspace, browse available skills, get skill instructions, find code snippets by language, or retrieve snippet content for a specific task.
data-ai
Handle agent questions and work gates in sgai workspaces. Use when an agent is blocked waiting for human input, when you need to respond to multi-choice questions, approve work gates, or provide free-text answers to agent queries.