Implementation Design Skill for ChatGPT: Draft File-level Changes, API Impact and Verification
Plan implementation from a supplied problem and code structure. Compare alternatives, then specify ordered changes, public impact, tests, and rollback conditions.
中文Install in ChatGPT
Requires a ChatGPT workspace where you can create skills. This is a text adaptation of the pinned GitHub source.
- Review the inputs and outputs in the pinned .claude/skills/design/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide the problem, constraints, file structure, public interface, and verification cases.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional CLI adds date filtering to an existing scan function while preserving the public API and workflow. Draft a plan and flag the undecided timezone.What to check
Keep no-filter behavior as default. Sequence arguments, core logic, workflow, and tests, with timezone and boundaries pending.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can a plan name a module whose existence is unverified?
Use supplied structure and symbols. Describe the module role when the path is unknown, then fill exact files after review.