code-reviewlisted

# Code Review ## What this skill is — and isn't | Skill | Question it answers | Output | |---|---|---| | `vd:scout` | "Where does this code live?" | Pointers | | `vd:debug` | "Why is this broken?" | Root cause | | **`vd:code-review`** | **"Is this change ready to land, and what should the author fix?"** | **Inline PR comments + summary verdict** | | `vd:ship` | "Land the branch." | Merged + tagged + PR | This skill **reviews and reports**. It does not implement fixes. If a fix is obvious and one-line, mention it in the comment as a suggestion — but don't apply it. Hand back to `vd:cook` / `vd:fix` for the actual work. ## Modes Auto-detect from arguments. Ambiguous or empty → `AskUserQuestion`. | Argument | Mode | Source of diff | |---|---|---| | `#123`, `123`, or GitHub PR URL | **PR** *(default & polished path)* | `gh pr diff` | | 7+ hex chars (`abc1234`) | **Commit** | `git show <sha>` | | `--pending` | **Pending** | `git diff` (staged + unstaged) | | `codebase` | **Codebase** | Broad scan via subagents | | *(none, recent changes in context)* | **Recent** | Whatever was just edited | Flags: - `--dry-run` — print the review payload, do NOT post to GitHub (PR mode only) - `--post` — opposite default; force posting even if other flags would skip - `--no-inline` — skip inline comments, post only the top-level summary - `--auto` — non-interactive, default answers, no prompts - `--ultra` — adversarial review via a dynamic workflow: every finding is independently refuted be