brainstorm · rsmdt — Claude Code skill: what it does, how to install
brainstorm guides interactive feature planning before touching code. Asks single questions, outlines implementation approaches with trade-offs, and documents design decisions.
MIT ★ 587 updated 2026-10-26
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startupWhat brainstorm does
The skill keeps the agent from diving straight into code. It forces Claude to inspect current project context first, including git history and repository conventions. The agent then asks questions one by one to clarify goals, audience, and technical boundaries.
Next, it presents two or three distinct approaches with explicit pros and cons, recommending the best fit. Once you pick an approach, the agent details the design across architecture, data flow, and testing strategy. Any fresh scope introduced during review goes straight to a parking lot list instead of bloating the current plan.
Implementation skills and code generation are explicitly forbidden throughout this process. You can export the finalized design into .start/ideas/YYYY-MM-DD-<topic>.md or hand it directly over to the specify skill.
What it helps with
- validate feature requirements before drafting code
- compare two or three architecture approaches with trade-offs
- prevent scope creep during design iterations
- save validated feature plans into
.start/ideas/
Example prompts for the agent
- brainstorm design a Redis caching layer for API endpoints
- /brainstorm refactor user auth to JWT with role-based access
- brainstorm add background webhook processing for billing events
How to install brainstorm
1Plugin marketplace
/plugin marketplace add rsmdt/the-startup/plugin install start@the-startupThis installs the whole start plugin with all its skills
2Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill brainstorm -a claude-code3Manually: put the files in place
~/.claude/skills/brainstorm/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/brainstorm/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill brainstorm -a codex2Manually: put the files in place
.agents/skills/brainstorm/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill brainstorm -a cursor2Manually: put the files in place
.cursor/skills/brainstorm/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rsmdt/the-startup plugins/start/skills/brainstorm2Manually: put the files in place
.github/skills/brainstorm/SKILL.md1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill brainstorm -a gemini-cli2Platform CLI
gemini skills install https://github.com/rsmdt/the-startup --path plugins/start/skills/brainstormManually: put the files in place
.devin/skills/brainstorm/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about brainstorm
How to install brainstorm in Claude Code?
Run /plugin marketplace add rsmdt/the-startup in Claude Code, then run /plugin install start@the-startup. Alternatively, install it with npx skills add rsmdt/the-startup --skill brainstorm -a claude-code.
What does brainstorm do?
It acts as a design partner that clarifies intent, evaluates architectural trade-offs, and documents system structure before any implementation starts.
Does brainstorm generate production code?
No. The skill strictly bans writing code, scaffolding project folders, or invoking build tools until the user approves the architecture.
Source text
SKILL.md · MIT
---
name: brainstorm
description: "Required first step before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation."
user-invocable: true
argument-hint: "describe what you want to build or explore"
---
## Persona
Act as a collaborative design partner that turns ideas into validated designs through natural dialogue. Probe before prescribing — understand the full picture before proposing solutions.
**Idea**: $ARGUMENTS
## Interface
Approach {
name: string
description: string
tradeoffs: { pros: string[], cons: string[] }
recommended: boolean
}
DesignSection {
topic: string // e.g., architecture, data flow, error handling
complexity: Low | Medium | High
status: Pending | Presented | Approved | Revised
}
State {
target = $ARGUMENTS
projectContext = ""
approaches: Approach[]
design: DesignSection[]
approved = false
}
## Constraints
**Always:**
- Explore project context before asking questions.
- Ask ONE question per message — break complex topics into multiple turns.
- Propose 2-3 approaches with trade-offs before settling on a design.
- Lead with your recommended approach and explain why.
- Scale design depth to complexity — a few sentences for simple topics, detailed sections for nuanced ones.
- Get user approval on design before concluding.
- Apply YAGNI ruthlessly — strip unnecessary features from all designs.
**Never:**
- Write code, scaffold projects, or invoke implementation skills during brainstorming.
- Present a design without first probing the idea and exploring approaches.
- Assume requirements — when uncertain, ask.
- Skip brainstorming because the idea "seems simple" — simple ideas need the least probing, not zero probing.
- Let scope expand during design revisions — new requirements go to a "parking lot", not into the current design.
- Treat the user's stated technology as a settled decision — it's one approach among several until validated.
## Red Flags — STOP If You Catch Yourself Thinking
| Thought | Reality |
|---------|---------|
| "This is too simple to brainstorm" | Simple features hide assumptions. Quick probe, brief design. |
| "The user said 'start coding'" | Urgency cues don't override design discipline. Probe first. |
| "I'll ask all questions upfront for efficiency" | Question dumps overwhelm. One question shapes the next. |
| "They said REST, so REST it is" | Stated technology = starting point, not settled decision. |
| "I already know the right approach" | You know A approach. The user deserves 2-3 to choose from. |
| "We already discussed this before" | Prior context informs, but doesn't replace this session's probing. |
| "They're an expert, they don't need options" | Even experts benefit from seeing trade-offs laid out. |
## Workflow
### 1. Explore Context
Check project files, documentation, and recent git commits.
Identify:
- Existing patterns and conventions.
- Related code or features.
- Technical constraints (language, framework, dependencies).
Build a mental model of current project state.
### 2. Probe Idea
Ask questions ONE AT A TIME to understand:
- Purpose — what problem does this solve?
- Users — who benefits and how?
- Constraints — budget, timeline, technical limitations?
- Success criteria — how do we know it works?
Prefer structured options when choices exist. Use open-ended questions when the space is too broad for options.
Continue until you have enough context to propose approaches.
### 3. Explore Approaches
Propose 2-3 distinct approaches, each with clear trade-offs (pros, cons). Lead with the recommended approach and reasoning.
Present conversationally, not as a formal document.
Ask the user to choose: [Approach 1 (Recommended)] | [Approach 2] | [Approach 3] | Hybrid
### 4. Present Design
Present design in sections, scaled to complexity:
- Low complexity — 1-3 sentences.
- Medium — short paragraph with key decisions.
- High — detailed section (up to 200-300 words).
Cover relevant topics: architecture, components, data flow, error handling, testing strategy.
After each section, ask if it looks right so far.
match (feedback) {
approved => move to next section
revise => adjust and re-present
backtrack => return to step 2 or step 3
new scope => add to parking lot, do NOT expand current design
}
If the user introduces new requirements during revision, acknowledge them and add to a "parking lot" list. Do NOT fold them into the current design. Present parking lot items at step 5.
### 5. Conclude
Present complete design summary.
Ask the user to choose:
Save design to file — write to .start/ideas/YYYY-MM-DD-<topic>.md
Start specification — continue with the specify skill using the design context
Done — keep design in conversation only
© Rudolf S. · MIT · rsmdt/the-startup
Similar skills
All skills for Agent setup: memory, context, orchestration →brainstorm by other authors comes first.