npx claudepluginhub levifig/loaf --plugin loafWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Captures ideas into structured nuggets for later evaluation. Use when the user says "I have an idea" or "note this down." Also activate when a specific actionable concept crystallizes during conversation. Without arguments, scans brainstorm documents for unprocessed sparks to promote.
This skill uses the workspace's default tool permissions.
templates/idea.mdIdea
Capture ideas quickly with minimal friction.
Input: $ARGUMENTS
Purpose
Ideas are raw nuggets -- unprocessed, unshaped, but worth remembering. The goal is speed of capture, not thoroughness. Shape later via /loaf:shape.
Process
Step 1: Parse Input
If $ARGUMENTS contains the idea, capture directly.
If $ARGUMENTS is empty, scan for sparks in brainstorm documents:
- Search
.agents/drafts/brainstorm-*.mdfor## Sparkssections - List unprocessed sparks (not marked as promoted or abandoned)
- Present the list and let the user pick one to promote
- When promoting: create idea file with
origin:field, mark spark as*(promoted)*in source document
If no sparks found and no arguments, ask at most 2-3 questions: core idea, problem/opportunity, immediate constraints.
Step 2: Generate Idea File
Create file in .agents/ideas/ following idea template.
Filename: {YYYYMMDD}-{slug}.md
Step 3: Create and Announce
- Generate timestamp:
date -u +"%Y-%m-%dT%H:%M:%SZ" - Create the file (infer title, tags, and related links without asking)
- Announce:
Captured: .agents/ideas/{filename}.mdwith next steps
Idea Lifecycle
raw -> shaping -> shaped (becomes SPEC) -> archived
| Status | Meaning |
|---|---|
raw | Just captured, unprocessed |
shaping | Being developed via /loaf:shape or /loaf:brainstorm |
shaped | Converted to SPEC, idea file archived |
archived | Decided not to pursue, kept for reference |
Guardrails
- Speed over completeness -- capture quickly, shape later
- 2-3 questions max -- don't turn this into an interview
- Infer, don't ask -- metadata should be automatic
- One idea per file -- keep them atomic
- No shaping here -- that's what
/loaf:shapeis for
Related Skills
- shape -- Develop an idea into a SPEC
- brainstorm -- Deep thinking on an idea or problem space (sparks from brainstorms can be promoted to ideas)
- research -- Investigate before capturing
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.