AugmentClaude

Brainstorming

Refine your idea into a complete design through collaborative questions and feedback.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/brainstorming-feiskyer/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use before building new features, components, or systems — explores intent, requirements, and design options through collaborative questions until the idea becomes a complete design. Not for bug fixes, config changes, or tasks with an obvious implementation path.

What this skill does

This skill guides you through transforming an initial idea into a complete, validated design before any implementation begins. It combines structured exploration—understanding project context, asking clarifying questions, and exploring alternative approaches—with iterative design presentation and approval cycles. The process culminates in a written specification document and a transition to a phased implementation plan.

What it does

  • Explores project context by reviewing existing files, documentation, and recent commits to understand the current state before diving into refinement
  • Asks clarifying questions one at a time to understand purpose, constraints, and success criteria, using multiple-choice options when practical
  • Presents 2–3 alternative design approaches with trade-off analysis and a reasoned recommendation
  • Presents the design in sections, matching detail level to complexity, and seeks user approval after each section
  • Writes a design specification document saved to docs/specs/YYYY-MM-DD-<topic>-design.md and committed to git
  • Performs self-review of the spec to catch placeholders, contradictions, ambiguities, and scope issues before user review
  • Transitions to implementation by creating a phased execution plan once the specification is approved

How to use it

Trigger this skill when you have a new feature, component, or system idea that needs refinement into a complete design—not for bug fixes, configuration changes, or tasks with an obvious path forward. Hand the skill your initial idea, and Claude will systematically explore your project context, ask targeted questions to clarify requirements, propose design options, present and refine the design with you, document it, and prepare a concrete implementation plan.

Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.

Related skills