From spec-superflow
Clarifies intent, scope, constraints, and success criteria before artifact creation. Useful for fuzzy requests, comparing options, or when a stable change definition is needed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spec-superflow:need-explorerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn a rough idea into a stable change definition before writing artifacts.
Turn a rough idea into a stable change definition before writing artifacts.
Agree on: problem, scope, non-goals, success criteria, whether to split before specification.
Before asking questions, understand what exists and what constraints are in place.
Ask a single clear question, wait for the answer, digest, then ask the next. Never ask 3+ questions at once. Each answer informs the next question.
Present 2-3 options when reasonable answers are finite. This reduces cognitive load and surfaces unconsidered choices.
For each approach: what it is, upside, downside, best-for. Then recommend one and explain why. Never present a single path — always name at least one alternative.
Restate what you heard: "Here's what I'm hearing: [problem, scope, non-goals, success criteria]. Does this match?" Incorporate corrections and re-validate.
After user confirms the summary:
node "${CLAUDE_PLUGIN_ROOT}/scripts/spec-superflow.mjs" state set <change-dir> dp_1_result "confirmed: <one-line summary>"
node "${CLAUDE_PLUGIN_ROOT}/scripts/spec-superflow.mjs" state set <change-dir> dp_1_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
DP-1 confirms scope, non-goals, and success criteria before artifact creation.
Once DP-1 is recorded, hand off to spec-writer.
You must leave exploration with: a usable change name, a crisp problem statement, scope boundaries, non-goals, success criteria, and a decomposition decision (one change or split).
Do not produce implementation code. This skill stabilizes intent, not builds.
npx claudepluginhub magebyte-zero/spec-superflow --plugin spec-superflowClarifies vague or ambiguous user requests by exploring the codebase first, then running an iterative Q&A loop until scope is clear.
Analyzes ambiguous task requests using 5W1H decomposition to surface assumptions and generate up to 3 targeted clarifying questions before execution.
Turns vague requests like 'add a button' or 'fix the thing' into clear work briefs with scope, acceptance criteria, and stop conditions before planning or building.