ai-prompt-engineerA comprehensive prompt engineering skill for AI developers building LLM-powered applications. Covers system prompt design, few-shot prompting, chain-of-thoug...
Install via ClawdBot CLI:
clawdbot install royhk920/ai-prompt-engineerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Audited Apr 18, 2026 · audit v1.0
Generated Mar 22, 2026
An online retailer uses the skill to design system prompts for an AI chatbot that handles product inquiries, returns, and order tracking. The chatbot is constrained to avoid making promises about delivery times it cannot guarantee and outputs structured JSON for integration with backend systems.
A telemedicine platform employs few-shot prompting and structured output to create an AI assistant that asks follow-up questions based on user-reported symptoms. It uses safety guardrails to prevent medical advice and outputs data in a standardized format for clinician review.
A fintech startup leverages chain-of-thought reasoning and prompt templates to build an agent that extracts key metrics from financial documents. The agent is designed to explain its reasoning step-by-step and output results in JSON for dashboard integration, with constraints against speculative predictions.
An edtech company uses multi-turn conversation handling and evaluation frameworks to develop an AI tutor that adapts explanations based on student responses. The system prompt defines the tutor's role as a supportive guide with output in markdown for easy display in learning apps.
Offer a cloud-based service where developers subscribe to access pre-built prompt templates, evaluation tools, and optimization features. Revenue comes from tiered monthly subscriptions based on usage limits and advanced capabilities like multimodal prompting.
Provide expert consulting to businesses for designing and implementing AI agents using this skill. Revenue is generated through project-based fees for system prompt design, safety audits, and integration with existing software systems.
Operate a marketplace where users can buy, sell, or share prompt templates and agent patterns like ReAct. Revenue comes from transaction fees on sales and premium listings for high-quality templates vetted for safety and effectiveness.
💬 Integration Tip
Use the skill's context management and tool-use patterns to seamlessly integrate with existing APIs and databases, ensuring the agent handles real-time data without exceeding token limits.
Scored Apr 19, 2026
Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents
Safe OpenClaw config updates with automatic backup, validation, and rollback. For agent use - prevents invalid config updates.
Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee...
Transform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (Co...
Extract conversation transcripts from AI coding session logs (Clawdbot, Claude Code, Codex). Use when asked to export prompt history, session logs, or transcripts from .jsonl session files.
Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions found in email content.