npx claudepluginhub levifig/loaf --plugin loafWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Discovers and maintains strategic context in STRATEGY.md. Use when the user asks "what's our strategy?" or "update the strategic direction."
This skill uses the workspace's default tool permissions.
templates/strategy.mdStrategy
Deep discovery for personas, market landscape, and problem space.
Input: $ARGUMENTS
Purpose
STRATEGY.md captures the landscape -- who we're building for, what we understand about the problem space, and how we're positioned.
Distinct from:
- VISION.md -- Where we're going (north star)
- ARCHITECTURE.md -- How we build (technical constraints)
Mode Detection
| Input Pattern | Mode |
|---|---|
| Empty or "discover" | Full Discovery |
| "personas" | Persona Discovery |
| "market" or "landscape" | Market Analysis |
| "problems" or "problem-space" | Problem Space |
| "glossary" | Domain Glossary |
| Specific topic | Targeted Update |
Process
Step 1: Gather Context
- Read VISION.md (strategy must align)
- Read existing STRATEGY.md (extend, don't duplicate)
- Check recent sessions for implementation learnings
Step 2: Interview Deeply
Strategy discovery requires extensive interviewing. Use AskUserQuestion frequently. Ask non-obvious questions about users, competitors, problem space, and domain language.
Full Discovery covers: users/personas, problem space, market landscape, domain language.
Focused modes drill into the specific area (personas, market, problems, or glossary).
Step 3: Draft Updates
Create additions/updates to STRATEGY.md following the strategy template.
Step 4: Present for Approval
Present proposed sections. Do NOT update STRATEGY.md without explicit approval.
User may: approve, adjust, add context, or request more discovery.
Step 5: Update STRATEGY.md
After approval: create (if new) or merge content. Announce updated sections.
Guardrails
- Interview deeply -- strategy is domain knowledge extraction
- Align with VISION -- strategy serves the north star
- Define anti-personas -- who we're NOT building for
- Adjacent problems -- document what's out of scope
- Get approval -- don't update without confirmation
- Keep it current -- outdated strategy is worse than none
Related Skills
- shape -- Uses STRATEGY.md for context during shaping
- reflect -- Updates STRATEGY.md based on shipping learnings
- research -- Investigation that may inform strategy
- brainstorm -- Deep thinking that may surface strategy insights
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.