brainstorming_skill
- Python
16
GitHub Stars
1
Bundled Files
3 weeks ago
Catalog Refreshed
2 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstart where the catalogue uses aiagentskills.
npx veilstart add skill technickai/ai-coding-config --skill brainstorming- SKILL.md5.5 KB
Overview
This skill turns rough ideas into clear, implementable designs through step-by-step collaborative dialogue. It focuses on understanding context, exploring distinct alternatives with tradeoffs, and validating each design section incrementally before implementation.
How this skill works
I start by exploring the current project state and asking a single, targeted question to clarify purpose, constraints, or success criteria. Next I present multiple distinct approaches, list tradeoffs for each, then make one clear recommendation and explain the decision criteria. After you approve, I build the design in small sections (architecture, data flow, error handling, tests) and validate each section before proceeding.
When to use it
- You have a rough idea but the implementation is unclear or incomplete.
- Multiple architectural approaches could work and you need to compare tradeoffs.
- Requirements are fuzzy and need refinement into testable success criteria.
- You want to validate design decisions before writing production code.
- You need a concise plan and commit-ready design document before development.
Best practices
- Ask one question at a time; prefer multiple-choice prompts to speed decisions.
- Always present distinct alternatives first, then make a single clear recommendation.
- Apply YAGNI: exclude speculative features that are not currently required.
- Validate each design section incrementally—architecture, data flow, errors, tests.
- Break the approved design into concrete implementation tasks and isolate work on a feature branch.
Example use cases
- Choosing between direct integration, event-driven messaging, or a separate service for a new feature.
- Refining vague product requirements into acceptance criteria and a test plan.
- Exploring tradeoffs for state management and caching strategies in a web app.
- Turning a high-level idea into a concise design doc and a task list for implementation.
- Validating whether added complexity (e.g., microservices) is justified by scaling needs.
FAQ
Typically 2–4 distinct approaches that explore the meaningful design space without overwhelming the discussion.
Will you combine approaches?
I avoid hybrid defaults. I recommend a single approach unless there's a compelling, specific reason a hybrid is necessary.
