npx claudepluginhub levifig/loaf --plugin loafWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Conducts deep, structured brainstorming with divergent thinking and trade-off analysis. Use when the user asks "help me think through this" or "what are the options?" Also activate when the user is thinking out loud, exploring tradeoffs, or comparing approaches without committing. Produces brainstorm documents with sparks (speculative byproducts) that can later be promoted to ideas via /idea.
This skill uses the workspace's default tool permissions.
Brainstorm
Think deeply about an existing idea or explore a new problem space.
Input: $ARGUMENTS
Purpose
Brainstorming is generative thinking -- expanding possibilities before narrowing.
Unlike /loaf:idea (quick capture) or /loaf:shape (rigorous bounding), brainstorming is exploratory: process an existing idea, explore a problem space, or generate options before committing.
Mode Detection
| Input Pattern | Mode |
|---|---|
| Idea file reference | Idea Processing (deep dive on captured idea) |
| Problem/question | Problem Exploration |
| Empty | Open Brainstorm ("What should we be thinking about?") |
Process
Idea Processing
- Read idea from
.agents/ideas/{filename}.md - Gather context: VISION.md, STRATEGY.md, ARCHITECTURE.md, related ideas
- Deep exploration: ask about user value, problem depth, alternatives, risks, dependencies, scope (minimal vs maximal)
- Generate options: conventional, minimal, ambitious, contrarian approaches
- Document with core insight, explored directions (approach/pros/cons), open questions, recommendation, next steps
- Update idea file status if proceeding
Problem Exploration
- Interview: problem definition, who's affected, impact, prior attempts, constraints
- Gather strategic context
- Diverge: first principles, inversion, analogy, extreme constraints, persona lens
- Converge: filter by strategy alignment, feasibility, value
- Document with problem statement, options, analysis, recommendation, next steps
Open Brainstorm
- Assess: list ideas in
.agents/ideas/, check recent sessions, review VISION for gaps - Surface opportunities: what's blocking? What's not being pursued? Untested assumptions?
- Present options for exploration
Capture Sparks (All Modes)
After the main brainstorm concludes, identify sparks -- speculative ideas that emerged but aren't part of the main direction. These are byproducts of exploration, not the conclusion.
Add a ## Sparks section at the end of the brainstorm document:
## Sparks
- **Title** -- one-line description
- **Title** -- one-line description
Sparks are:
- Lightweight -- one bullet, one line each. Don't expand or analyze.
- Byproducts -- they emerged during brainstorming, not the main output
- Worth remembering -- interesting enough to not lose, not ready for
/loaf:shape
Spark lifecycle:
- Unprocessed (default) -- sitting in the brainstorm document
*(promoted)*-- processed into an idea via/loaf:idea~~Strikethrough~~ *(abandoned)*-- decided not to pursue
Brainstorm documents are archived, never deleted -- they hold exploration context, reasoning, and unprocessed sparks. A brainstorm doc remains active while it has unprocessed sparks.
Guardrails
- Diverge before converging -- generate options before judging
- Stay exploratory -- don't prematurely commit
- Document the thinking -- even discarded options are valuable
- Connect to strategy -- ground exploration in context
- Know when to stop -- set boundaries on exploration
Related Skills
- idea -- Quick capture (may precede brainstorming)
- shape -- Rigorous bounding (often follows brainstorming)
- research -- Fact-finding (complements brainstorming)
- strategy -- Strategic context (grounds brainstorming)
Similar Skills
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.