prototype-question
Skill4 starsChanged 18 days agoMITView on GitHub
Define the decision, evidence target, scope, fidelity, and stopping rule for a product prototype. Use before building when the prototype risks becoming a polished demo without a testable question. Do not use when the user has already supplied an equally precise prototype brief.
In this repository9 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 43
Do not prototype the entire product to answer a local question.
- Distinctive: line 44
Do not confuse stakeholder approval, visual polish, or successful generation with user evidence.
- Distinctive: line 45
Never conceal simulated AI, data, payments, permissions, or destructive actions from test participants.
- Distinctive: line 46
If no plausible observation could change the decision, recommend a different evidence method.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prototype Question
Design the smallest artifact that can make one important unknown observable.
Frame the probe
- Name the decision the prototype should inform and the highest-risk assumption behind it.
- Choose one primary question. Move secondary questions to a later list.
- Identify who must experience or inspect the prototype and in what context.
- Select the minimum fidelity required for credible evidence:
- representation for structure or comprehension;
- clickable flow for navigation or interaction;
- coded behavior for state, timing, AI behavior, feasibility, or instrumentation;
- concierge or Wizard-of-Oz behavior when the system can be simulated honestly.
- Specify which states and branches must be real, which may be simulated, and what must be disclosed.
- Define evidence collection and support / reject / reframe criteria.
- Set a stopping rule for both building and testing.
Output
## Decision this prototype informs
## Primary unknown
## Audience and context
## Minimum prototype
- Fidelity:
- Must be real:
- May be simulated:
- Out of scope:
## Evidence plan
## Support / reject / reframe criteria
## Stop rule
## Result handoffBoundaries
- Do not prototype the entire product to answer a local question.
- Do not confuse stakeholder approval, visual polish, or successful generation with user evidence.
- Never conceal simulated AI, data, payments, permissions, or destructive actions from test participants.
- If no plausible observation could change the decision, recommend a different evidence method.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

