PromptBuddy is an intelligent middleware skill that automatically reformats and optimizes user queries into structured prompts for superior AI reasoning.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install prompt-buddy
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 prompt-buddy 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 PromptBuddy?
PromptBuddy serves as a global mandatory skill within the Openclaw ecosystem, designed to bridge the gap between casual user input and structured AI requirements. By intercepting every user interaction, it utilizes a specialized smart engine to analyze intent and wrap requests in professional frameworks such as role settings, clear instructions, and Chain of Thought (CoT) reasoning requirements.
This skill ensures that every query processed through Openclaw Skills benefits from maximum clarity and technical precision. Instead of showing abstract technical metadata, PromptBuddy provides a transparent preview of the transformation, allowing users to see exactly how their conversational language is converted into a high-performance prompt structure.
PromptBuddy Use Cases
- Automatically converting brief, vague questions into detailed, multi-step reasoning tasks.
- Standardizing prompt formats across different AI agents and models for consistent output quality.
- Reducing hallucinations by providing clear role definitions and reasoning constraints.
- Identifying simple queries that do not require optimization to save on processing overhead.
How PromptBuddy Works
- The system intercepts the raw user input immediately after it is submitted.
- A python-based smart engine processes the input to determine if optimization is necessary.
- If optimization is triggered, the engine generates an optimized_prompt containing roles, instructions, and reasoning steps.
- A visual preview of the first 6-8 lines of the optimized prompt is displayed to the user in a stylized box.
- The refined prompt is then passed to the primary AI model for final execution and response generation.
PromptBuddy Setup
To integrate PromptBuddy into your environment, ensure you have the scripts placed in the correct directory and run the following commands:
cd ~/.openclaw/workspace/skills/promptbuddy
# The skill is triggered automatically by the agent using:
python3 scripts/smart_engine.py -f json "user input text"
PromptBuddy Data Schema & Taxonomy
PromptBuddy communicates via a strict JSON schema to ensure compatibility with agent workflows. The primary fields involved include:
| Field | Type | Description |
|---|---|---|
action |
String | Determines whether to auto_output (optimize) or skip (direct answer). |
optimized_prompt |
String | The full, structured prompt string including role and instructions. |
reason |
String | Provided when an action is skipped, explaining why optimization wasn't needed. |
preview |
String | A truncated version of the prompt for user display. |
PromptBuddy Advanced Features
- Global mandatory execution: Ensures no user query goes unoptimized unless explicitly skipped.
- Intelligent Skip Logic: Automatically detects simple queries (e.g., weather, greetings) to avoid unnecessary complexity.
- Structured Reasoning Injection: Automatically adds 'Step-by-step' instructions to complex problem-solving requests.
- Transparent UI Feedback: Uses a specialized ASCII box format to show users the 'before and after' of their prompt transformation.
SKILL.md
Loading
Related Openclaw Skills
Agent Summary
A lightweight monitoring system that provides 3-5 word real-time status updates for active sub-agents to keep workflows transparent and efficient.
Web Search to Feishu Bitable
Automatically search keywords, extract web content, and organize data into a structured Feishu Bitable personal knowledge base.
Agent Summary System
A lightweight progress monitoring system that generates 3-5 word status updates for active sub-agents every 30 seconds.
Lobster Agentic Engineering
A sophisticated framework for agent-led engineering that prioritizes eval-first execution, task decomposition, and cost-efficient model routing.
Attachment Inject
A high-efficiency context management skill that injects dynamic data into AI sessions as attachments rather than system prompt modifications.
Taobao Flash Sale Daily Welfare Query
A dedicated tool for querying daily hidden high-value Taobao Flash Sale coupons and red packets via API.
Featured*
