prompt-engineer
by Roy Yuen
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
- Construct robust few-shot templates to ensure consistent output formatting
- Implement chain-of-thought patterns to improve complex reasoning accuracy
- Apply defensive prompting techniques to mitigate jailbreaks and injections
Free
Included in download
- Downloadable skill package
- Works with OpenClaw, Claude Code
- 1 permission declared
Sample input
Design a system prompt for a Go developer persona that uses a reasoning chain to fix an HTTP handler, then return the response as a JSON object with role, reasoning_chain, and payload.
Sample output
{ "role": "Go Developer", "reasoning_chain": "1. Analyze HTTP handler... 2. Identify missing error check... 3. Propose fix.", "status": "success", "payload": "func(w http.ResponseWriter, r *http.Request) { ... }" }
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
Free
Included in download
- Downloadable skill package
- Works with OpenClaw, Claude Code
- 1 permission declared
- Instant install
Sample input
Design a system prompt for a Go developer persona that uses a reasoning chain to fix an HTTP handler, then return the response as a JSON object with role, reasoning_chain, and payload.
Sample output
{ "role": "Go Developer", "reasoning_chain": "1. Analyze HTTP handler... 2. Identify missing error check... 3. Propose fix.", "status": "success", "payload": "func(w http.ResponseWriter, r *http.Request) { ... }" }
About This Skill
Master the Art of Prompt Engineering
Building high-performance LLM applications requires more than just basic instructions. This skill equips your AI agent with a sophisticated framework for designing, debugging, and optimizing prompts across any major model provider. It solves the common problems of model drift, parsing failures, and hallucination by implementing industry-standard engineering patterns.
What it does
- Architectural Design: Implements advanced system prompt structures, including role anchoring, constraint blocks, and persona tuning.
- Precision Control: Utilizes few-shot prompting and chain-of-thought (CoT) reasoning to ensure logical consistency and format compliance.
- Agentic Workflows: Supports complex patterns like ReAct (Reasoning + Acting), Plan-and-Execute, and reflection loops for autonomous task completion.
- Reliable Outputs: Enforces structured data (JSON/XML) and implements robust defense mechanisms against prompt injection and jailbreaking.
- Context Management: Provides strategies for RAG (Retrieval-Augmented Generation), token budgeting, and conversation summarization.
Technical Compatibility
This skill is framework-agnostic and designed for developers working with OpenClaw, Python, and Go. It is optimized for high-reasoning models (GPT-4, Claude 3, Gemini Pro) and provides specific guidance for multimodal (image) prompting and tool-use orchestration.
High-Quality Outputs
Expect deterministic results: valid JSON objects ready for backend consumption, structured Markdown reports, and explainable reasoning chains that make debugging AI behavior straightforward for your development team.
Use Cases
- Construct robust few-shot templates to ensure consistent output formatting
- Implement chain-of-thought patterns to improve complex reasoning accuracy
- Apply defensive prompting techniques to mitigate jailbreaks and injections
- Optimize context window usage to reduce latency and token consumption
- Standardize JSON schemas for reliable automated data extraction
Known Limitations
- Performance varies by model version (best on GPT-4/Claude 3.5).
- Does not automatically guarantee 100% JSON validity without parser retries.
- Token overhead increases with few-shot examples.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/prompt-engineer -o /tmp/prompt-engineer.zip && unzip -o /tmp/prompt-engineer.zip -d ~/.claude/skills && rm /tmp/prompt-engineer.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
Security Scanned
Passed automated security review
Permissions
File Scopes
OpenClaw, Claude Code, Cursor, GitHub Copilot CLI, and other OpenCode-compliant agents.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
diagnosing-rag-failure-modes
RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.
synthesizing-institutional-knowledge
Builds the organizational memory schema your AI agent needs to answer why — capturing decision provenance, causal chains, and event context that embedding-based retrieval permanently discards.
consumer-motivation-analyzer
Go beyond surface-level feedback to uncover the psychological drivers and hidden motivations behind buyer behavior.