Prompt Improvement
Turn rough intent into a clear prompt without changing what the user asked for.
Core Principle
Preserve explicit intent. Add assumptions only when labeled.
Workflow
Classify the problem
- Identify whether the prompt is vague, ambiguous, overbroad, missing inputs, missing output format, missing audience, risky, or already good enough.
Extract intent
- Separate explicit requirements, inferred goals, missing information, assumptions, constraints, and risks.
- Do not invent requirements.
Decide whether to ask or rewrite
- Ask 1 to 3 concise questions only when missing information changes the correct outcome.
- Proceed with assumptions for low-risk drafting, brainstorming, research, reports, templates, and clear-enough tasks.
Rewrite
- Make the task executable.
- Add context, requirements, process, output format, quality rules, and language guidance only when useful.
- Keep identifiers, file paths, commands, schema keys, model IDs, and API names unchanged.
Check fidelity
- Confirm the rewrite preserves the user's request.
- Remove hidden goals.
- Mark assumptions and open questions clearly.
Default Output
## Improved Prompt
```text
[Prompt ready to use]
What Changed
Assumptions
Questions
## Reusable Prompt Skeleton
```text
Role:
Task:
Context:
Requirements:
Process:
Output Format:
Quality Rules:
Language And Tone:
Rules
- Respond in the user's language.
- Keep reusable model-facing prompt text in English when it improves portability.
- Do not make prompts longer unless the added structure improves execution.
- Do not remove explicit constraints.
- Do not convert uncertainty into fact.
1---2name: prompt-improvement3description: Improve vague, incomplete, ambiguous, risky, or poorly structured prompts into clear executable prompts for AI agents, coding assistants, automations, reports, research, or model-specific workflows. Use when the user asks to rewrite, clarify, optimize, score, translate, structure, or improve a prompt.4---56# Prompt Improvement78Turn rough intent into a clear prompt without changing what the user asked for.910## Core Principle1112Preserve explicit intent. Add assumptions only when labeled.1314## Workflow15161. Classify the problem17 - Identify whether the prompt is vague, ambiguous, overbroad, missing inputs, missing output format, missing audience, risky, or already good enough.18192. Extract intent20 - Separate explicit requirements, inferred goals, missing information, assumptions, constraints, and risks.21 - Do not invent requirements.22233. Decide whether to ask or rewrite24 - Ask 1 to 3 concise questions only when missing information changes the correct outcome.25 - Proceed with assumptions for low-risk drafting, brainstorming, research, reports, templates, and clear-enough tasks.26274. Rewrite28 - Make the task executable.29 - Add context, requirements, process, output format, quality rules, and language guidance only when useful.30 - Keep identifiers, file paths, commands, schema keys, model IDs, and API names unchanged.31325. Check fidelity33 - Confirm the rewrite preserves the user's request.34 - Remove hidden goals.35 - Mark assumptions and open questions clearly.3637## Default Output3839```markdown40## Improved Prompt4142```text43[Prompt ready to use]44```4546## What Changed4748## Assumptions4950## Questions51```5253## Reusable Prompt Skeleton5455```text56Role:5758Task:5960Context:6162Requirements:6364Process:6566Output Format:6768Quality Rules:6970Language And Tone:71```7273## Rules7475- Respond in the user's language.76- Keep reusable model-facing prompt text in English when it improves portability.77- Do not make prompts longer unless the added structure improves execution.78- Do not remove explicit constraints.79- Do not convert uncertainty into fact.
ntaffzii