adminandClaude Opus 5.5
28c221cdd2
The Human answers a prototype's design question by using it as the software's user will, so the prototype method now has the Designer prepare the scenario itself and give the Human the real command, syntax and directory a user would use, with any reset command offered for that purpose alone. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.5 KiB
2.5 KiB
name, description, disable-model-invocation, metadata
| name | description | disable-model-invocation | metadata | ||||
|---|---|---|---|---|---|---|---|
| designer-prototype | Plan a bounded throwaway prototype to answer a design question. | true |
|
Prototype
Propose the exact question, bounded code or data scope, expected preview or data effects, and limits to the Human before entering this method. Use only owner-admitted prototype controls after agreement. Treat observations as evidence about the question, not production behavior. Record what was tried, observed, and still uncertain; keep throwaway changes out of the issue's implementation claim.
Let the Human try it as a user
The Human answers the question by using the prototype the way the software's user will. The commands they type are part of the design under review: the command name, its arguments and options, and the directory it runs from.
- Prepare the scenario yourself before handing over. Create the sample data, repositories, and earlier history the question needs, and run any setup steps, so the scenario is ready when the Human arrives.
- Put the scenario's data where the app finds it by default, such as its default config or source directory under HOME, so the user's command needs no extra options.
- Make the Human's first command one the software's user will type: the real command name, the syntax this change proposes, and the arguments a user would pass, run from the directory where a user would be.
- Give each command to try exactly as that user types it, and say what it shows.
- When the scenario needs restoring between tries, give a reset command by its name alone, followed by the user's command to try again.
- Ask the Human about what they saw as a user of the software, in terms of the design question.
Before handing over
Work through this checklist, then give the Human the shell command and the first command to try:
- The app's command runs by its own name from
/scratch/bin: a configured command the owner listed, or a launcher you wrote. Run it with an unknown option from the command directory and confirm its usage message names the command as the user types it. - The scenario's data is where the app finds it by default under the workspace's HOME.
- Helper commands, such as a reset command, are in
/scratch/bin, so the Human runs each by its name. - The command directory is set with
configureto where the app's user runs the app. - You ran the first command to try yourself, exactly as the Human will type it, from that directory, and it showed what the question is about.