Help us improve
Share bugs, ideas, or general feedback.
From groundwork
Clarifies feature requests via targeted questions on problems, users, outcomes, and detects contradictions in proposed requirements.
npx claudepluginhub etr/groundworkHow this skill is triggered — by the user, by Claude, or both
Slash command
/groundwork:understanding-feature-requestsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive workflow for clarifying feature requests and ensuring they don't conflict with existing requirements.
Clarifies vague requests via Socratic questioning, focusing on one key uncertainty (goals, scope, constraints, completion criteria) at a time to produce actionable requirements. Activates on deep-interview requests or unclear specs.
Conducts structured requirements-gathering interviews for software features/systems. Reads SPEC.md and context, asks numbered questions on purpose, technical design, UI/UX, edge cases, security, rollout. For deep requirement elicitation before specs/plans.
Analyzes ambiguous task requests using 5W1H decomposition to surface assumptions and generate up to 3 targeted clarifying questions before execution.
Share bugs, ideas, or general feedback.
Interactive workflow for clarifying feature requests and ensuring they don't conflict with existing requirements.
Your current effort level is {{effort_level}}.
Skip this step silently if effort is high or higher AND you are Sonnet or Opus.
If effort is 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.
When the user proposes a feature or change, ask clarifying questions to understand:
Core Questions (always ask):
Exploratory Questions (for open-ended or vague requests):
Conditional Questions (ask as relevant):
Keep questions focused - ask 2-3 at a time, not all at once. Build understanding iteratively.
Question Style:
Before proceeding with design, review for conflicts within the proposed feature:
If conflicts found, surface them and resolve before proceeding.