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
Structure
Completeness
Guardrails
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
1---2name: prompt-optimization3description: Use when auditing an existing prompt for clarity, structure, or completeness issues, fixing vague instructions, or producing a before/after optimization report.4---56<objective>7Prompt 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).89It 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.10</objective>1112# Prompt Optimization1314Skill for analyzing and improving existing prompts.1516## References1718- [common-problems.md](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)19- [improvement-techniques.md](references/improvement-techniques.md) - Load when: strengthening a prompt with Chain-of-Thought, few-shot examples, or reinforced guardrails20- [scorecard-template.md](references/scorecard-template.md) - Load when: writing the before/after optimization report to hand off2122## Optimization Workflow2324```251. ANALYZE current prompt26 ↓272. IDENTIFY issues28 ↓293. APPLY corrections30 ↓314. VALIDATE improvement32 ↓335. DOCUMENT changes34```3536## Analysis Checklist3738### Clarity39- [ ] Unambiguous instructions?40- [ ] Clearly defined objective?41- [ ] Precise vocabulary?4243### Structure44- [ ] Well-delimited sections?45- [ ] Logical order?46- [ ] Clear hierarchy?4748### Completeness49- [ ] Output format defined?50- [ ] Error cases handled?51- [ ] Examples if needed?5253### Guardrails54- [ ] Explicit limits?55- [ ] Forbidden behaviors listed?56- [ ] Appropriate security?5758For common problem patterns with before/after fixes, see [common-problems.md](references/common-problems.md). For techniques to strengthen a prompt (CoT, examples, guardrails), see [improvement-techniques.md](references/improvement-techniques.md).5960## Forbidden6162- Never change the original meaning of the prompt63- Never add unrequested features64- Never remove existing guardrails65- Never make the prompt longer without justification
fusengine