| name | clarify-intent |
| description | Use when a task is classified design or build, before exploring solutions — pin the real goal (not the means), the constraints and key assumptions, and the success criteria, then show them to the human. Part of meta-workflow (Step ①); runs upstream of superpowers brainstorming. |
Step ① — Clarify what you are really doing
Why this exists: it is easy to do the right thing in the wrong direction. Before exploring
how, fix what counts as the problem solved — otherwise every later step is efficient motion
toward the wrong place.
Done = all three pieces are pinned
1. The real goal — what, and why.
Chase it to the real goal: a means is not a goal. "Build an oracle" is a means; "the
extractions are accurate" is the goal. The current task is usually a means to a higher goal — ask
one level up: this artifact serves what?
2. Constraints + key assumptions — each rated importance × certainty.
Include dependency constraints, and run the circular-dependency check: your measure must not
depend on the thing it measures. (Judging extraction quality by the recall of that same extraction
is circular — it will tell you what you want to hear.)
3. Success criteria (seed) — 1–3, each tagged measurable or judgment.
Give judgment ones a semi-objective anchor (e.g. "audit the existing store with a rule — is
what it flags agreed garbage?"). These seed the expected values in the Step ② acceptance table.
Light vs heavy
Default to the full version. Fast-path only when all three pieces are writable on the spot
and none is a low-certainty judgment call. Even the fast path must show the three pieces to the
human to invite correction — "I've decided it's clear" is not a license to skip silently. If you
can't tell which path → take the full one.
A confident-sounding human ("just follow the spec") does not mean the three pieces are done —
check means-vs-goal and circular dependency anyway.
Relationship to superpowers
This is upstream of brainstorming. Brainstorming explores solutions; this fixes what counts
as the problem solved. Pin the three pieces here, get a thumbs-up, then hand off to
superpowers brainstorming for solution exploration. Design/build tasks go through this even if
you're tempted to brainstorm directly.
