reprompter
Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aytuncyildizli/reprompterWhat This Skill Does
RePrompter v7.0 is the premier OpenClaw skill designed to elevate your AI interactions by transforming raw, messy prompts into highly structured, actionable, and effective instructions. Whether you are working with a single agent or orchestrating complex multi-agent systems, RePrompter acts as an intelligent architect. It operates in two distinct modes: 'Single' for refining individual prompts through a brief, focused interview, and 'Repromptception' for complex tasks requiring team orchestration, multi-agent planning, and iterative quality control. The skill utilizes best-practice frameworks—including XML tag structures and defined constraints—to ensure your agent output achieves a quality score of 7/10 or higher for single tasks and 8+/10 for multi-agent workflows.
Installation
To integrate RePrompter into your agent workflow, run the following command in your terminal:
clawhub install openclaw/skills/skills/aytuncyildizli/reprompter
Use Cases
RePrompter is essential when the quality of your agent's response is dependent on the clarity of your instructions. Ideal scenarios include:
- Converting informal, vague requirements into technical specifications for development agents.
- Structuring multi-step workflows involving parallel processing, such as a security audit paired with a cost analysis.
- Preparing complex prompts for model-based reasoning, where XML-based constraints significantly reduce hallucination and improve logic.
- Improving the output quality of long-running tasks where performance metrics matter.
Example Prompts
- "reprompt this: write a backend API for user authentication with JWT, make it secure."
- "repromptception: I need an audit of our database schema performance and a parallel review of our frontend rendering speed."
- "clean up this prompt: summarize these meeting notes and identify three actionable tasks for the engineering team."
Tips & Limitations
- When to Use: Always utilize RePrompter for tasks involving multi-domain systems, audits, or complex reasoning requirements.
- Limitations: Avoid using this skill for trivial, single-turn interactions, casual chat, or simple Q&A. The overhead of the interview process is counter-productive for simple queries.
- The Interview Gate: If your input is too brief (e.g., 'hi'), the skill will prompt you for more detail. Always provide a clear verb or objective to bypass the guardrails and start the optimization process immediately.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aytuncyildizli-reprompter": {
"enabled": true,
"auto_update": true
}
}
}