A systematic prompt engineering framework based on 9 core rules designed to drastically improve AI response quality and logical consistency.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install claude-prompt-engineering
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install claude-prompt-engineering using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Prompt Engineering Master?
The Prompt Engineering Master skill is a technical framework designed to optimize the performance of AI agents by applying 9 systematic rules derived from Claude Code best practices. It addresses common issues like hallucinations, redundant explanations, and lost context in long conversations. By integrating this skill into Openclaw Skills, developers can ensure their AI assistants follow a modular, constraint-first, and self-verifying workflow.
This skill transforms vague user queries into structured tasks by enforcing a specific logical lifecycle. It prioritizes negative constraints (what the AI must NOT do) and requires active restatement of needs before any execution begins, ensuring that the AI truly understands the objective before generating output.
Prompt Engineering Master Use Cases
- Refining technical documentation to be more concise and direct without losing critical details.
- Performing high-accuracy code reviews where the AI is forbidden from saying everything looks fine without verification.
- Querying complex information where the AI must explicitly state if it does not know the answer instead of guessing.
- Managing long-running data analysis tasks where rule adherence often drifts over time.
How Prompt Engineering Master Works
- The user triggers the skill via specific keywords like prompt master or by setting the AUTO_APPLY_PROMPT_RULES environment variable.
- The skill injects a prioritized system prompt containing the 9 core rules, focusing on modularity and conclusion-first formatting.
- For complex tasks, the AI is forced to restate the user's requirements and wait for confirmation before execution.
- Upon completion, the AI performs a self-verification process against a quality checklist to ensure all constraints were met.
- The final output is delivered in a concise, list-based format with the core conclusion presented first.
Prompt Engineering Master Setup
To activate this skill within Openclaw Skills, you can configure the settings in your local configuration file. Use the following structure in your .openclaw/config.json:
{
"skills": {
"prompt-engineering": {
"autoApply": true,
"defaultMode": "full"
}
}
}
You can also trigger it manually during a session by typing apply prompt rules.
Prompt Engineering Master Data Schema & Taxonomy
The skill manages prompt logic through a structured configuration and template system. It organizes rules based on task categories to maximize efficiency in Openclaw Skills.
| Feature | Description | Key Mode |
|---|---|---|
| Rule Injection | Full 9-rule set or minimal core constraints | full / minimal |
| Task Templates | Specialized structures for code, writing, and analysis | custom |
| Verification | Pre-output self-check and post-output validation | strict |
| Memory Management | Periodic re-confirmation of rules in long threads | full |
Prompt Engineering Master Advanced Features
- Dynamic Rule Selection: Automatically chooses the most effective subset of rules based on whether the task is creative writing, code review, or data analysis.
- Enforcement Modes: Choose between Minimal (low token usage), Full (standard optimization), and Strict (maximum reliability for mission-critical tasks).
- Built-in Memory Management: Actively restates key constraints every 10 conversation rounds to prevent instruction loss in large context windows.
- Quality Assurance Hooks: Integrated checklists that the AI must complete internally before presenting any final result to the user.
SKILL.md
Loading
Related Openclaw Skills
Pylon
A comprehensive integration for managing Pylon data and automating analytical workflows through the Membrane interface.
Workato
A comprehensive iPaaS integration that enables AI agents to orchestrate business workflows and manage records across cloud applications via Workato.
Budget Travel Deals
An intelligent travel scout that uncovers hidden gem destinations by scanning for the lowest flight and hotel prices paired with high-quality attractions.
slash-tokens
A high-performance Rust CLI proxy that filters terminal output to reduce AI token consumption by up to 90%.
Amazon Review Scraper - VOC Intelligence
A powerful AI-driven tool for Amazon sellers to automatically fetch and analyze product reviews using VOC.AI and Claude AI.
Prediction Market Arbitrage
A specialized tool for autonomous agents to detect and analyze price discrepancies between major prediction markets like Polymarket and Kalshi.
Featured*
