ADR Skill for ChatGPT: Draft an Architecture Decision Record
Record a technical or product choice in the Nygard ADR format. Capture the context, alternatives, decision, and consequences in Markdown a team can revisit after implementation.
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 pm-execution/skills/adr/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for adr 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 adr 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
A fictional inventory service exports about 500 rows every night. Option A generates a CSV on request and may slow listing at peak time. Option B generates and caches a file nightly with up to 24 hours of delay. The team chose B. Draft ADR-012 and state a trigger for revisiting it.What to check
The ADR should identify B, record its data delay, preserve on-demand generation as an alternative, and state the fallback or open question for a cache failure. It should name a review trigger such as the need for hourly data.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can I record a decision that has already taken effect?
Yes. Mark the status as accepted and record the decision date. If a later decision replaces it, write a new ADR and mark the old one as superseded so its reasoning remains available.