claude-code-review.yml

# Automatic Claude Code review of pull requests.
#
# Runs the upstream `code-review@claude-code-plugins` plugin so we pick up
# any improvements to the canonical review skill, then layers a
# Quarto/R-specific addendum on top so the reviewer also catches issues
# particular to this manuscript template repo.
#
# Each run posts a fresh review comment; prior reviews are left in place
# so the PR keeps a visible history rather than a rolling sticky.
#
# Skips drafts, Dependabot bumps, and fork PRs (fork PRs can't read repo
# secrets). Project guidance is in CLAUDE.md. Requires the
# CLAUDE_CODE_OAUTH_TOKEN repository secret.

name: Claude Code Review

on:
  pull_request:
    types: [opened, synchronize, ready_for_review, reopened]
  workflow_dispatch:
    inputs:
      pr_number:
        description: 'Pull request number to review'
        required: true
        type: number

concurrency:
  group: claude-review-${{ github.event.pull_request.number || inputs.pr_number }}
  cancel-in-progress: true

jobs:
  claude-review:
    if: |
      github.event_name == 'workflow_dispatch' ||
      (github.event.pull_request.draft == false &&
       github.event.pull_request.user.login != 'dependabot[bot]' &&
       github.event.pull_request.head.repo.full_name == github.repository)
    runs-on: ubuntu-latest
    env:
      PR_NUMBER: ${{ github.event.pull_request.number || inputs.pr_number }}
    permissions:
      contents: read
      pull-requests: write
      issues: read
      id-token: write

    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 1
          submodules: recursive

      - name: Claude PR review
        uses: anthropics/claude-code-action@v1
        with:
          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
          allowed_bots: "github-actions[bot]"
          plugin_marketplaces: 'https://github.com/anthropics/claude-code.git'
          plugins: 'code-review@claude-code-plugins'
          track_progress: ${{ github.event_name == 'pull_request' && 'true' || 'false' }}
          prompt: |
            /code-review:code-review ${{ github.repository }}/pull/${{ env.PR_NUMBER }}

            In addition to the standard checks above, this is the qmt Quarto
            manuscript template — prose-heavy, multi-format, and re-used as a
            template for downstream manuscripts — so also prioritize:

            1. **Quarto / prose correctness**
               - `.qmd` syntax: chunk options use `#|` directives, fenced
                 blocks are balanced, cross-refs (`@fig-`, `@tbl-`, `@sec-`)
                 resolve to defined labels.
               - Author YAML: name, ORCID, affiliations, and `corresponding`
                 fields are well-formed.
               - Supplementary notebooks listed in `_quarto.yml` under
                 `manuscript: notebooks:` exist and have matching labels.
               - Bullet-list rule: 3+ items use bullets with a blank line above.
               - `code-fold: true` is used on chunks where the output (not the
                 code) is the point, and avoided on analysis-narrative code.

            2. **R code**
               - Conforms to `.lintr.R` settings (snake_case, line length, etc.).
               - No new package dependencies without justification — every
                 dependency added here lands in every downstream manuscript.

            3. **Build hygiene**
               - No accidental commits of `_manuscript/`, `_freeze/`, or `.quarto/`.
               - `README.md` is generated; edits should go to `README.Rmd`.
               - Bibliography entries in `references.bib` are well-formed BibTeX
                 with DOIs for articles and books.

            4. **CI / template impact**
               - Workflow changes don't break the `copilot-setup-steps.yml`
                 contract or the publish/preview pipelines.
               - Spell-check / link-check failures are fixed at the source
                 (wordlist or content) rather than suppressed.

            **Post line-specific findings as inline review comments** anchored
            to the relevant line(s). Reserve the top-level summary for a brief
            overall verdict plus any finding not tied to a specific line.
            Skip generic praise — be concrete. If the PR looks clean, say so briefly.

          claude_args: |
            --allowedTools "mcp__github_inline_comment__create_inline_comment,Bash(gh pr view:*),Bash(gh pr diff:*),Bash(gh pr comment create:*)"