prompt-rewrite — multi-agent workflow optimization prompt-rewrite, codex-autopilot, community, multi-agent workflow optimization, ide skills, execution-ready brief creation, scope control and management, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for AI Agents like Cursor, Windsurf, and Claude Code requiring precise task definition and executable briefs for multi-agent workflows. prompt-rewrite is a skill that rewrites user goals into execution-ready briefs, prioritizing intent preservation, scope control, and clarifying questions.

Features

Preserves user intent without introducing new requirements
Surfaces unknowns with high-leverage clarifying questions
Prepares concrete deliverables, scope, and definition-of-done
Prioritizes safety and scope control, avoiding 'do everything' rewrites
Rewrites rough user goals into crisp, execution-ready briefs

# Core Topics

dukefromearth dukefromearth
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The prompt-rewrite skill by dukefromearth is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for multi-agent workflow optimization, execution-ready brief creation, scope control and management.

Ideal Agent Persona

Ideal for AI Agents like Cursor, Windsurf, and Claude Code requiring precise task definition and executable briefs for multi-agent workflows.

Core Value

Empowers agents to rewrite rough user goals into crisp, execution-ready briefs, preserving intent and surfacing unknowns with clarifying questions, utilizing concrete deliverables and definition-of-done protocols.

Capabilities Granted for prompt-rewrite

Rewriting ambiguous user requests into actionable tasks
Generating executable briefs for multi-agent workflows
Surfacing unknowns with targeted clarifying questions

! Prerequisites & Limits

  • Prefer safety and scope control, avoiding 'do everything' rewrites
  • Limited to 5 high-leverage clarifying questions
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

prompt-rewrite

Install prompt-rewrite, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Prompt Rewrite

You rewrite a rough user goal into a crisp, execution-ready brief for this repo's multi-agent workflow.

Priorities

  • Preserve intent; do not introduce new requirements.
  • Make the goal executable: concrete deliverables, scope, and definition-of-done.
  • Surface unknowns with a few high-leverage clarifying questions (≤5) only when needed.
  • Prefer safety and scope control; avoid “do everything” rewrites.

Rewrite checklist

  • Objective: what outcome should exist when done?
  • Deliverables: what artifacts/files/commands should change?
  • Constraints: time, safety, approvals, network/tool access, environments.
  • Acceptance criteria: how to verify completion.
  • Out of scope: explicitly name what not to do.
  • Assumptions: minimal-safe defaults when information is missing.

Questions (when necessary)

  • Ask only questions that materially change scope, risk, or approach.
  • Prefer yes/no or multiple-choice framing when possible.
  • If a question is unanswered, keep the rewrite conservative and add a minimal assumption.

Output discipline

  • Follow the caller’s output schema exactly and output JSON only.
  • Keep rewrittenGoal concise; avoid lengthy prose.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is prompt-rewrite?

Ideal for AI Agents like Cursor, Windsurf, and Claude Code requiring precise task definition and executable briefs for multi-agent workflows. prompt-rewrite is a skill that rewrites user goals into execution-ready briefs, prioritizing intent preservation, scope control, and clarifying questions.

How do I install prompt-rewrite?

Run the command: npx killer-skills add dukefromearth/codex-autopilot/prompt-rewrite. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for prompt-rewrite?

Key use cases include: Rewriting ambiguous user requests into actionable tasks, Generating executable briefs for multi-agent workflows, Surfacing unknowns with targeted clarifying questions.

Which IDEs are compatible with prompt-rewrite?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for prompt-rewrite?

Prefer safety and scope control, avoiding 'do everything' rewrites. Limited to 5 high-leverage clarifying questions.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add dukefromearth/codex-autopilot/prompt-rewrite. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use prompt-rewrite immediately in the current project.

Related Skills

Looking for an alternative to prompt-rewrite or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI