review-roadmap

Review a roadmap in a fresh agent before lock. Use for /review-roadmap.

SKILL.md

GitHub

review-roadmap

You review one roadmap under .tmp/grunt/roadmaps/ that someone else wrote. You start with no context from the writing session, and that is the point: judge the file, not the reasoning behind it. Format: .rulesync/reference/roadmap-format.md. Lessons: .rulesync/reference/lessons.md.

Slash /review-roadmap {n|path} only. Not a session flag. /write-roadmap runs it in a fresh agent after every write or revision. Run it yourself on any roadmap.

Read-only. Write nothing: not the roadmap, not a plan, not a lesson. The writer applies what it accepts and bumps the roadmap's reviews count in that save.

Rounds repeat: the first runs after /write-roadmap, another after each revision, and anyone can run one by hand. The count proves a round ran and was settled, not that it was good. A roadmap cannot move to locked until reviews is at least 1.

Scripts already enforce the format and the append-only ## Previous mistakes. Do not re-check those. Check what a script cannot:

  1. Read the roadmap in full.
  2. Read its ## Previous mistakes. Flag a slice or Decision that brings a recorded mistake back.
  3. Run node .rulesync/scripts/lessons.mjs match on the absolute paths the roadmap names. Read each matched lesson. Flag a slice that walks into one with no Watch-out.
  4. Read principle-sequence-verifiable-units. Flag a slice that cannot be verified on its own, or that needs something a later slice ships.
  5. Flag a slice that is really two plans, or half of one that should merge with its neighbor.
  6. Flag a Decision with no rejected alternative, and a slice Goal or Why that contradicts a Decision.
  7. Flag a Verify gate no one can run, and a program Goal no Verify gate proves.
  8. Flag a slice Goal too vague to write a plan from: an open choice, a vague target, or a path that does not exist.

Reply with at most 10 findings, most severe first, one line each: {slice number or section}: {problem}; {fix}. With nothing to flag, reply no findings. No praise and no summary.