mcpField
P
prompt-optimization

prompt-optimization

github.com/fusengineAgent workflows3460 installsUpdated 1d ago
Repository

About prompt-optimization

Prompt Optimization is a skill for reviewing and refining existing prompts while preserving their original meaning and guardrails. It guides prompt authors through analysis, correction, validation, and documenting changes.

Key features

  1. 01Five-step prompt refinement workflow
  2. 02Checks clarity, structure, completeness, and guardrails
  3. 03Uses examples for common prompt problems
  4. 04Supports CoT, few-shot, and guardrail techniques
  5. 05Provides an optimization report template

Use cases

  1. 01Clarifying ambiguous prompt instructions
  2. 02Checking prompts for missing output or error handling
  3. 03Strengthening prompts without changing their intent

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/fusengine/claude-plugins --skill prompt-optimization

After installing, type/prompt-optimizationin Claude Code to confirm it loaded.

Details

From the project README
Prompt Optimization analyzes and improves an existing prompt through a 5-step workflow: analyze the current prompt, identify issues, apply corrections, validate the improvement, and document the changes. Its checklist covers four dimensions -- clarity (unambiguous instructions, precise vocabulary), structure (well-delimited sections, logical order), completeness (output format, error cases, examples), and guardrails (explicit limits, forbidden behaviors, security).

It never changes the prompt's original meaning, adds unrequested features, removes existing guardrails, or lengthens the prompt without justification. See common-problems.md for before/after fix patterns and improvement-techniques.md for strengthening via CoT, few-shot, or guardrails.

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

Comments

Markdown supported