Prompt Engineering Guide Claude Skill — Production Prompts Template

Engineer prompts that work in production: structure, examples, constraints, output format, and eval loops. From one-shot to multi-step, this is the working playbook.

What this Claude Skill does

• Structure prompts with role, task, context, constraints, and output format
• Build few-shot examples that improve accuracy without bloating tokens
• Design output formats that downstream code can parse reliably
• Set up eval loops to measure prompt quality over time

Built for

• AI engineers shipping prompts to production
• Founders writing their own prompts and wanting to do it right
• Agencies training teams on prompt craft

What's inside

• SKILL.md — the full skill file with frontmatter, methodology, phases, examples, anti-patterns, and recovery
• Step-by-step phases Claude follows to produce a senior-level output every time
• Worked examples with realistic detail you can adapt to your situation
• Anti-patterns + recovery playbook so the work survives edge cases
• Delivery file tree so outputs land organized for you or your client

How a Claude Skill works

This is a Claude Skill — a single SKILL.md file Claude reads as instructions for a specific kind of work. Drop it in your Claude Project, your /mnt/skills/user/ folder, or wherever Claude can read it. Claude triggers the skill automatically when your prompt matches its description, then follows the methodology end to end.

Author

Built by Ukiyo Productions — a strategy-led branding and growth agency. Part of a 100+ skill marketplace built for founders, operators, consultants, and agencies.