mr-reviewlisted

Get independent external-AI reviews on a merge request and post them as MR comments: sends the MR title, description, and diff to each configured external reviewer — OpenAI GPT (correctness-first implementation brief) and xAI Grok (code-quality review: DRY, cohesion, naming, testability) — and posts each reviewer's brief as a separate MR discussion. The point is independence: the reviewers are DIFFERENT models from the one that wrote the code, so they don't share its blind spots. Review-only — never modifies code, never approves, never merges. Feeds /address-review, which triages and resolves the posted comments. Requires OPENAI_API_KEY and/or XAI_API_KEY in the environment (see Configuration). Use when: "review this MR", "run the AI review", "get an external review", right after /build-feature raises an MR, or re-reviewing after fixes were pushed.
ohyesgocool/feature-loop · ★ 0 · Code & Development · score 70

Install: claude install-skill ohyesgocool/feature-loop

# MR Review Run the review stage of the feature loop: collect the MR's real diff, hand it to **external** reviewer models, and post their briefs back onto the MR as comments. You orchestrate; the reviews themselves come from models that did not write the code — that independence is the value, so post their output **verbatim**, never edited, softened, or summarized by you. This skill is **review-only**: it never modifies code, pushes commits, approves, or merges. The follow-up — deciding which findings hold and fixing them — is `/address-review`'s job. If the user provided arguments: `$ARGUMENTS` — an MR number or URL. With no arguments, auto-detect the current branch's open MR (`glab mr list --source-branch "$(git branch --show-current)"`). > **Forge note.** Written for GitLab (`glab`). On GitHub: `gh pr view` / `gh pr diff` to gather > context, `gh pr comment <n> --body-file <brief.md>` to post each review. Process identical. ## Configuration All configuration is environment variables — set them in your shell profile, or in your agent's settings (for Claude Code, the `env` block of `~/.claude/settings.json`); see the repo README: | Variable | Required | Default | Purpose | |---|---|---|---| | `OPENAI_API_KEY` | for the GPT reviewer | — | correctness-first implementation brief | | `OPENAI_MODEL` | no | `gpt-5.5` | which OpenAI model reviews | | `XAI_API_KEY` | for the Grok reviewer | — | code-quality review brief | | `XAI_MODEL` | no | `grok-4.3` | which xAI model revi