DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to draft a design spec one section at a time with Elephant Goldfish Model

Turn a rough concept brief into a living design document built section by section.

Who it is forA product-minded engineer who has a concept brief and needs a structured design doc without starting from a blank page.

The problemWriting a full specification in one pass is slow, and the structure often drifts from what the team needs to decide.

The outcomeA markdown design document under docs/designs/ that was compiled section by section from the concept brief.

What you need first

  • An AI coding agent that can install the plugin, such as Claude Code or Codex, or any agent that can take the install request from the README
  • A local git checkout of the project you are designing for
  • A design doc file under docs/designs/ to review, or a concept to start from

Steps

  1. Install the plugin in your agent, for example in Claude Code with claude plugin marketplace add google/elephant-goldfish-model && claude plugin install egm@egm
  2. Place your concept brief in the repo, or describe it to the agent
  3. Run /egm-draft and answer the questions it asks for each section
  4. Save the output as a markdown file under docs/designs/
  5. Run /egm-review on the file before you open a pull request

Prompt for your agent

Using the EGM plugin in <repo-path>, run /egm-draft on the concept brief at <brief-path> and write the result to docs/designs/<name>.md. Confirm that the file has a section for each part of the brief and list any part you could not fill in.

Caveat. The README describes the drafting skill but does not show its exact prompts, so expect to check each section the agent writes against your own decisions.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page