understanding-feature-requests

Understanding Feature Requests

Interactive workflow for clarifying feature requests and ensuring they don't conflict with existing requirements.

Pre-flight: Model Recommendation

Your current effort level is {{effort_level}}.

Skip this step silently if effort is high, xhigh, or max (the scale is low < medium < high < xhigh < max, so xhigh and max are already above high) AND you are Sonnet or Opus. If effort is low or medium (i.e. below high), you MUST show the recommendation prompt — regardless of model. If you are not Sonnet or Opus, you MUST show the recommendation prompt - regardless of effort level.

Otherwise → use AskUserQuestion:

{
  "questions": [{
    "question": "Do you want to switch? Contradiction detection in feature requirements benefits from consistent reasoning.\n\nTo switch: cancel, run `/effort high` (and `/model sonnet` if on Haiku), then re-invoke this skill.",
    "header": "Recommended: Sonnet or Opus at high effort",
    "options": [
      { "label": "Continue" },
      { "label": "Cancel — I'll switch first" }
    ],
    "multiSelect": false
  }]
}

If the user selects "Cancel — I'll switch first": output the switching commands above and stop. Do not proceed with the skill.

Step 1: Clarify the Request

When the user proposes a feature or change, ask clarifying questions to understand:

Core Questions (always ask):

• What problem does this solve for the user?
• Who is the target user/persona?
• What is the expected outcome or behavior?

Exploratory Questions (for open-ended or vague requests):

• "What inspired this feature idea?"
• "Have you seen this done well elsewhere? What did you like about it?"
• "What would make this feature 'delightful' vs just 'adequate'?"
• "What's the simplest version that would provide value?"
• "If you had to cut half the scope, what would you keep?"

Conditional Questions (ask as relevant):

• What triggers this behavior? (for event-driven features)
• What are the edge cases or error conditions?
• What is explicitly out of scope?
• Are there dependencies on other features?
• What metrics would indicate success?
• How could this fail? What are the possible risks and dangers?
• Could we do this in any other way?