plugins/core/skills/brainstorming/SKILL.md
This skill should be used before implementing features, building components, or making changes when requirements need clarification. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when multiple valid interpretations exist.
npx skillsauth add rbozydar/rbw-claude-code 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.
Clarify WHAT to build before diving into HOW to build it.
Brainstorm when:
Skip when:
Before diving into questions, assess whether brainstorming is needed.
Clear requirements signals: specific acceptance criteria, referenced patterns, exact expected behavior, constrained scope.
Brainstorming needed signals: vague terms ("make it better"), multiple interpretations, undiscussed trade-offs.
If requirements are clear, suggest proceeding directly to planning or implementation.
Ask questions one at a time to understand intent. Avoid overwhelming with multiple questions.
Question techniques:
Key topics: Purpose/motivation, Users/context, Constraints/timeline, Success criteria, Edge cases, Existing patterns in the codebase.
Exit condition: Continue until the idea is clear OR user says "proceed."
Propose 2-3 concrete approaches:
### Approach A: [Name]
[2-3 sentence description]
**Pros:** [Benefits]
**Cons:** [Drawbacks]
**Best when:** [Circumstances]
Lead with a recommendation. Be honest about trade-offs. Consider YAGNI -- simpler is usually better.
Summarize key decisions:
---
date: YYYY-MM-DD
topic: <kebab-case-topic>
---
# <Topic Title>
## What We're Building
[1-2 paragraphs]
## Why This Approach
[Approaches considered and rationale]
## Key Decisions
- [Decision]: [Rationale]
## Open Questions
- [Unresolved questions]
## Next Steps
→ `/workflows:plan` for implementation details
Output location: docs/brainstorms/YYYY-MM-DD-<topic>-brainstorm.md
Present options:
/workflows:planKeep sections short (200-300 words max). After each section, pause to validate: "Does this match what you had in mind?" This prevents wasted effort on misaligned designs.
Exploration mode (divergent): Generate many options without judgment. Use when requirements are unclear or early in brainstorming. Challenge assumptions, consider radical alternatives. Use the gemini-brainstorm agent for external perspectives and the devils-advocate-brainstormer agent to stress-test emerging ideas.
Convergence mode (focused): Narrow to a decision. Use when options are clear and trade-offs understood. Compare against success criteria, apply constraints as filters.
Always confirm mode transitions with the user.
| Anti-Pattern | Better Approach | |--------------|-----------------| | Asking 5 questions at once | Ask one at a time | | Jumping to implementation | Stay focused on WHAT, not HOW | | Overly complex solutions | Start simple, add complexity only if needed | | Ignoring codebase patterns | Research what exists first | | Assumptions without validation | State and confirm assumptions | | Lengthy design documents | Keep concise -- details go in the plan | | Skipping success criteria | Ask early how success will be measured | | Anchoring on first solution | Present 2-3 options before recommending |
Brainstorming answers WHAT -- requirements, chosen approach, key decisions. Planning answers HOW -- implementation steps, code patterns, testing strategy.
When brainstorm output exists, /workflows:plan should detect it and use it as input.
development
This skill should be loaded when writing, reviewing, or refactoring Python code to apply strict coding standards directly in the current context without spawning a subagent. It provides comprehensive Python development standards covering SOLID principles, asyncio patterns, type hints, testing, and production-quality code.
tools
This skill should be used when invoking the Gemini CLI for code review, plan review, or any prompt-based task. It provides correct invocation patterns emphasizing stdin piping and @ syntax over shell variable gymnastics.
development
Use this skill when writing, reviewing, or debugging Quickshell configurations (QML files for desktop shell UI on Wayland/Hyprland). Triggers on: QML files with Quickshell imports, shell.qml entry points, PanelWindow or FloatingWindow usage, Quickshell service integration (PipeWire, MPRIS, notifications, Hyprland IPC), Wayland layer-shell or session-lock code, custom bar/panel/widget/dock/OSD/lockscreen/launcher development, or any question about building a desktop shell with Quickshell on Hyprland.
development
This skill should be used when thorough, multi-perspective research with citations is needed. It performs comprehensive research using a diffusion research loop with domain specialization, supporting general web research and specialized domains (geopolitical with GDELT). Auto-detects domain from query or accepts an explicit --domain flag.