Streamlit Spec Writing Skill for ChatGPT: Draft Product and Technical Proposals
Organize proposals using the Streamlit product and technical spec structure. Start with user problems and examples, then state candidate APIs, behavior, trade-offs, and review questions.
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/writing-spec/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide the feature proposal, user problem, existing API, and supporting trade-off evidence.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional widget needs an empty-data preview. Users currently supply custom placeholder text. Options are a new parameter or extending an existing one. Outline product and technical specs.What to check
Keep the user job, minimal use, and empty behavior in the product spec. Compare parameter options and compatibility in the tech spec. Mark state and rerun behavior for review.
Original SKILL.md on GitHub · Updated
Frequently asked question
When would one feature need two specs?
Use both when user-visible behavior and underlying design require substantial decisions. Minor changes can follow the project's ordinary documentation convention.