maestroprompt-leverage

name	maestro:prompt-leverage
description	Strengthen a raw user prompt into an execution-ready instruction set for Claude Code, Amp, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.

Prompt Leverage

Turn the user's current prompt into a stronger working prompt without changing the underlying intent. Preserve the task, fill in missing execution structure, and add only enough scaffolding to improve reliability.

Core principle: A prompt is strong when removing any part of it would make the output worse. Everything else is noise.

When to Use

Always:

• Multi-step coding tasks (refactor, feature, migration)
• Research or analysis with specific deliverables
• Prompts destined for CLAUDE.md, AGENTS.md, or similar persistent instructions
• Reusable templates or hooks

Sometimes (light touch only):

• Single-file bug fixes with clear reproduction
• Writing tasks with well-defined audience and format

Never (skip prompt leverage entirely):

• One-shot questions ("What does this function do?")
• Simple commands ("Run the tests", "Format this file")
• Tasks the agent already handles well without scaffolding

Thinking "this simple task needs full framework blocks"? Stop. That is over-engineering. A three-line task needs a three-line prompt.

The Proportionality Principle

Prompt scaffolding should be proportional to task complexity.
More scaffolding than needed = noise that dilutes real instructions.

Task Complexity	Scaffolding Level

``` Fix the login bug ``` No context. Which bug? What file? What should happen? ``` Fix: `handleLogin` in src/auth/login.ts returns 200 on invalid password. Expected: return 401 with { error: "Invalid credentials" }. Verify: existing auth tests pass after the fix. ``` Three lines. Objective, expected behavior, verification. Nothing more needed. ``` Refactor the database layer to use connection pooling instead of creating a new connection per request. ``` Missing: which files, what pool library, constraints, done criteria. ``` ## Objective Refactor the database layer (src/db/) to use connection pooling. Replace per-request connections with a shared pool using the existing `pg` library's built-in Pool class.