reviewlisted
Install: claude install-skill rjmurillo/ai-agents
# Review
Review: $ARGUMENTS
If no argument, review the current branch diff against the base branch. Detect the base branch from `gh pr view --json baseRefName` or fall back to `main`.
## Triggers
| Trigger Phrase | Operation |
|----------------|-----------|
| `/review` | Run the Stage-1 spec-compliance gate, then the Stage-2 review against the current branch diff |
| `/review BRANCH_OR_PR` | Run the Stage-1 gate, then the Stage-2 review against the named branch or PR |
| `review before merge` | Same as `/review` |
## Convergence contract (REQ-008-04)
`/review` evaluates every canonical axis the project ships, plus three local-only skill axes that CI cannot afford. The canonical axis prompts are authored at `references/{role}.md` co-located with this skill, with the canonical path expressed as `.claude/skills/review/references/{role}.md` in the source repo (the single source of truth). `/review` auto-discovers the axis set from `references/*.md` rather than hardcoding a list, so adding a `references/{role}.md` file enrolls the axis with no edit to this skill body. When CI exists in a project, the project syncs the canonical axes into its own CI prompts via the project's generator and drift checks. The build pipeline copies the entire skill directory (including `references/` and `scripts/`) into vendored plugin installs so the command runs without a CI dependency in any harness that supports plugins.
The canonical set is `spec-compliance` as the Stage-1 gate plus 11 Stag