Skip to content

/prompt-engineering

A deep, practical guide to engineering reliable LLM prompts — role/context, instructions, few-shot, structured output, chain-of-thought, delimiting untrusted data, injection defense, and evaluation. Includes worked prompts and a runnable output validator.

shell
$ npx -y skills add vanara-agents/skills --skill prompt-engineering --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/prompt-engineering
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

A deep, practical guide to engineering reliable LLM prompts — role/context, instructions, few-shot, structured output, chain-of-thought, delimiting untrusted data, injection defense, and evaluation. Includes worked prompts and a runnable output validator.
Ships withvanara-agents-skills

🐒 Free agents, skills & packs for Claude Code One subscription. An army of Claude Code agents. 30 production-grade agents, skills, and packs for Claude Code — free, Apache-2.0, install with one command.

Get the whole plugin, auto-invoked
Stats
9
Stars
0
Views
3
Forks
Active
Maintenance
JavaScript
Language
Apache-2.0
License
7d ago
Last commit
21d ago
Created

Repo: vanara-agents/skills

Other skills on vanara-agents-skills.