Brainstorming Ideas Into Designs
Paste the following prompt into your AI chat to install this skill:
Install @user_142af50a/brainstorming-v2 into your AI assistant according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem Addressed
Many agents jump into coding, scaffolding, or implementation checklists before requirements are clear. This skill helps convert a vague idea into a reviewable design spec before any implementation work begins.
How It Works
The skill enforces a structured workflow: inspect files, docs, and recent commits; clarify purpose, constraints, and success criteria one question at a time, preferring multiple-choice options. If the topic involves UI, diagrams, or layout, it can offer a visual companion as a separate message to show mockups, comparisons, and architecture sketches. It then proposes 2-3 approaches with trade-offs and a recommendation, presents the design section by section covering architecture, components, data flow, error handling, and testing, and asks for approval after each section. The approved spec is written to docs/superpowers/specs/YYYY-MM-DD--design.md, checked for placeholders, contradictions, scope, and ambiguity, committed to Git, and reviewed by the user. Only after approval does it hand off to writing-plans.
Boundaries
This is useful for unclear feature design, refactoring direction, or decomposing large systems. It may be too heavy for simple, fully specified changes or emergency fixes. The skill is limited to design clarification and spec production; it should not trigger implementation skills before user approval.
Use Cases
- Clarify a vague feature idea into purpose, constraints, success criteria, and a reviewable spec before coding.
- Define boundaries, interfaces, dependencies, and test strategy for an over-responsible module before refactoring.
- Separate conceptual UI questions from visual layout choices and compare mockups or flows when designing interfaces.
- Break a large platform request into independent sub-projects and produce a spec for the first sub-project.
Best For
- Product engineers who need to turn requirement notes into approved design direction before implementation.
- Maintenance engineers who want to clarify module boundaries and interfaces before touching legacy code.
- Full-stack engineers building small utilities who need a concise, actionable spec from an initial idea.
- Tech leads who want a consistent design-discussion workflow and a committed spec for feature kickoffs.
Related Skills
Run a grilling session to interact with or test AI agents.
A systematic prompt optimization skill that refines prompts using a four-step distillation framework (diagnose, structure, think, compress) and methodologies from four prompting masters.
Tencent Cloud OCR agent for K-12 exam grading with async full-sheet or single-question marking, handwritten answer recognition, correctness, knowledge points, and coordinates.
Quickly converts a user's input, list, or screenshot into a multi-page workbench, supporting template selection, custom builds, and responsive layouts.