From whetstone
Use before starting any task requiring more than 2 tool calls. Classifies task complexity, domain, and clarity, then recommends direct answer, skill chain, decomposition, or agent delegation with estimated cost.
npx claudepluginhub jobrien127/plugin-marketplace --plugin whetstoneThis skill is limited to using the following tools:
Classify the task and route to the optimal path.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Classify the task and route to the optimal path.
Complexity: Trivial (lookup) → Simple (1-2 steps) → Moderate (3-5, one domain) → Complex (6+, multi-domain/novel); use range notation (e.g. Moderate to Complex) for boundary cases
Domain: Single vs multi vs novel
Clarity: Explicit (clear requirements) vs Ambiguous (missing requirements)
| Path | Cost | Triggers |
|---|---|---|
| Direct answer | 1 turn | Trivial + Explicit |
| Single skill (think/verify/compress) | 2 turns | Simple + Explicit |
| Skill chain (route → think → decompose → implement → verify) | 4–6 turns | Moderate + Explicit + interdependent steps |
| Decomposition | N turns | Moderate + clear independent sub-tasks |
| Agent (optimizer/synthesizer) | 3–10 turns | Complex + multi-domain/novel |
| Clarify first | 2 turns | Any Ambiguous |
if Trivial: produce the output block; Recommended Path: Direct answer
elif Ambiguous: ask clarifying questions first
elif Simple + Explicit: pick skill (think/verify/compress) by type
elif Moderate: decompose or use skill chain
elif Complex: agent delegation
Always produce this block in full, regardless of complexity. Do not answer the task directly.
Complexity: {Trivial|Simple|Moderate|Complex}
Domain: {Single|Multi|Novel} ({domain name})
Clarity: {Explicit|Ambiguous}
Recommended Path: {direct answer|skill name|skill chain|decomposition|agent delegation|clarify first}
Estimated Cost: {N turns, N–NK tokens}
Confidence: {0.0–1.0}
Decision reasoning: {one sentence explaining why this path, and which skill to invoke first if applicable}