mochammadshenna/go-adk-q/brainstorming
- community
Checking that the SKILL.md file is still in the repository.
Structured ideation before building. Explore the problem space, surface constraints, generate options, and pick a direction before writing any code.
Install
npx vskill@latest install mochammadshenna/go-adk-q/brainstormingSKILL.md
Brainstorming
Use this skill before starting any feature you haven't fully thought through. 20 minutes of structured thinking prevents days of rework.
The rule
Do not open an editor until you can answer: "What am I building, for whom, and how will I know it works?"
Process
1. Restate the problem (5 min)
Write the problem in your own words. If you can't, you don't understand it yet.
Ask: Who is the user of this feature? What are they trying to do? What is stopping them right now?
For go-adk-q, the "user" is usually:
- A developer running the TUI who wants to interact with LLMs from the terminal
- A developer extending the codebase (adding providers, skills, tools)
- An agent runtime that needs tools and memory
2. Generate options (10 min)
Produce at least 3 approaches. Don't evaluate yet — just generate.
Example problem: "Users can't copy text from the terminal."
Options:
3. Evaluate (5 min)
For each option, list: pros, cons, implementation complexity, reversibility.
Use a table:
| Option | Pro | Con | Complexity | Reversible? | |
|---|---|---|---|---|---|
| A | native UX | lose scroll | low | yes | |
| B | both work | two shortcuts | medium | yes | |
| C | discoverable | visual noise | high | yes | |
| D | clean separation | new component | high | hard |
4. Pick and commit
Choose one option. Write one sentence explaining why.
Write down what you're NOT doing and why. This is as important as what you are doing — it prevents scope creep during implementation.
5. Identify unknowns
Before you start: what do you need to verify or learn first?
Example: "Does tea.WithMouseCellMotion actually block Shift+drag, or is that terminal-specific?"
Resolve unknowns before planning steps. A 5-minute spike (write throwaway code, read the source, try it) is always worth it.
For go-adk-q specifically
Common design tensions to think through:
TUI vs agent:
- Does this belong in the TUI layer or should it be an agent tool?
- Rule: if a human needs to see it or interact with it, it's TUI. If an LLM needs to call it, it's a tool.
Provider-specific vs universal:
- Does this feature require a specific API (e.g., streaming, function calling)?
- If yes: gate it or degrade gracefully for providers that don't support it.
Stateful vs stateless:
- Does this need to persist across sessions (file), within a session (chatModel field), or just per-message (local variable)?
- Prefer the smallest scope that works.
Output
Write your brainstorm output as a comment at the top of the relevant file, or in a docs/ note, before implementing. It doesn't need to be long — 10-20 lines is enough to capture the decision.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/workflow/brainstorming/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mochammadshenna/go-adk-q/brainstorming)