independent-review
When to Use
Load this skill when the user asks for an independent review of an artifact (spec, plan, design, code, document).
Arguments
The user's arguments/flags (e.g. --ux) arrive as plain text with the invocation. Wherever the steps below refer to "the user's arguments", use that text.
Independent review (separate agent)
When a step calls for an independent review, run it in a fresh context — a subagent (Claude Code Agent tool), a new Codex/Cursor chat, or a teammate — that gets only this skill and the artifact, never the author's reasoning. Instruct it to be read-only; since most agent runtimes cannot enforce that, verify afterward that the reviewer made no edits (git status unchanged) before accepting its verdict.
Review Workflow
📁 Source note:
[sage]= upstream Sage repo (github.com/xoai/sage, public) — optional deeper reading; this skill runs fully on the rules inlined here. A step marked MUST READ points at a file in your own project (e.g. an event registry) — if it is missing, stop and ask instead of improvising.
Independent evaluation. Designed to work in a fresh session for maximum objectivity, but also works within an existing session.