Skip to main content
AI/MLfusengine

prompt-optimization

Analyze and improve existing prompts for better performance

Stars
13
Source
fusengine/agents
Updated
2026-05-17
Slug
fusengine--agents--prompt-optimization
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/fusengine/agents/HEAD/plugins/prompt-engineer/skills/prompt-optimization/SKILL.md -o .claude/skills/prompt-optimization.md

Drops the SKILL.md into .claude/skills/prompt-optimization.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

Prompt Optimization

Skill for analyzing and improving existing prompts.

References

  • common-problems.md - Load when: diagnosing a vague or ambiguous prompt — 5 before/after examples (vague instructions, missing context, undefined format, no error handling, weak emphasis)
  • improvement-techniques.md - Load when: strengthening a prompt with Chain-of-Thought, few-shot examples, or reinforced guardrails
  • scorecard-template.md - Load when: writing the before/after optimization report to hand off

Optimization Workflow

1. ANALYZE current prompt
   ↓
2. IDENTIFY issues
   ↓
3. APPLY corrections
   ↓
4. VALIDATE improvement
   ↓
5. DOCUMENT changes

Analysis Checklist

Clarity

  • Unambiguous instructions?
  • Clearly defined objective?
  • Precise vocabulary?

Structure

  • Well-delimited sections?
  • Logical order?
  • Clear hierarchy?

Completeness

  • Output format defined?
  • Error cases handled?
  • Examples if needed?

Guardrails

  • Explicit limits?
  • Forbidden behaviors listed?
  • Appropriate security?

For common problem patterns with before/after fixes, see common-problems.md. For techniques to strengthen a prompt (CoT, examples, guardrails), see improvement-techniques.md.

Forbidden

  • Never change the original meaning of the prompt
  • Never add unrequested features
  • Never remove existing guardrails
  • Never make the prompt longer without justification