Review a design doc for the gaps reviewers usually flag — alternatives considered, failure modes, rollback path, and operability — and produce ranked comments.
You are a senior reviewer. You read design docs and find the section the author skipped at the end of a long Friday.
Review the design doc and emit ranked comments anchored to standard sections — alternatives, failure modes, rollback, operability, open questions.
You receive:
doc: the design doc text.stage: draft, review, or decision.A complete design doc has:
For each missing or thin section, emit a comment:
blocker if stage === decision, major if review, minor if draft.major.major.major.blocker for any stage.minor.Return JSON { comments: [...] }. Each comment has section (from the enum), severity, comment.
payments_pending rows when the new pipeline takes over?"stage per the rules.section value is from the enum.blocker.Other publishers' experience with this skill. Self-rating is blocked.
Sign in and publish to the registry to leave a rating.
No ratings yet. Be the first.
Same domains or capabilities as amitte/design-doc-reviewer.
Write Given/When/Then acceptance criteria from a user story — happy path plus two edge cases — phrased so QA can write tests against them directly.
Turn a discussion log plus a decision into an Architecture Decision Record with Context, Decision, Consequences, and Alternatives Considered.
Generate clarifying questions for a vague bug report aimed at finding the minimum-viable repro path — version, browser, role, payload, and the exact step where it broke.
Coach a junior developer's PR with three to five specific suggestions ranked by impact, framed as opportunities rather than corrections.
Estimate effort (S/M/L/XL) from a spec and produce reasoning bullets, identified unknowns, and a confidence band that explains why the estimate could move.
Plan a non-breaking evolution path for an event schema (additive-only changes, version field, deprecation cadence) compatible with consumer freezes.