System Prompt Structure Skill for ChatGPT: Separate Role, Boundaries, and Format
Draft a system prompt with a role, context, behavior rules, output requirements, and examples. Use the sections to make long prompt rules easier to test.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download claude-plugin/prompt-architecture/skills/system-prompt-structure/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for system-prompt-structure together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that system-prompt-structure appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
Design a fictional library assistant. It answers borrowing questions from supplied library rules and returns a conclusion, evidence, and missing information. Add one normal example and one question the materials do not cover.What to check
The draft should explain the source boundary and unknown-case behavior. Both examples should return all three fields. The uncovered case should flag missing information without inventing a return date.
Original SKILL.md on GitHub · Updated
Frequently asked question
Should the prompt list every way a user might ask a question?
Define the role, rules, and output first. Add a few examples for boundaries and edge cases, then check that different phrasings follow the same rules.