zadanthony/meta-workflow/clarify-intent

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.