diff --git a/.github/workflows/code-review.yml b/.github/workflows/code-review.yml
new file mode 100644
index 0000000..a32d4fb
--- /dev/null
+++ b/.github/workflows/code-review.yml
@@ -0,0 +1,72 @@
+name: code-review
+
+on:
+  pull_request:
+    # Review a pull request when it opens or becomes ready, and again
+    # after each push to it.
+    types: [opened, reopened, ready_for_review, synchronize]
+
+permissions:
+  contents: read
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+jobs:
+  review:
+    # GitHub withholds repository secrets from pull requests opened
+    # from a fork, so the review runs only on branches pushed to
+    # this repository.
+    if: >-
+      github.event.pull_request.draft == false &&
+      github.event.pull_request.head.repo.full_name == github.repository
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      # Full history, so the review can walk each commit in the PR.
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      # The action does not run a slash command given as its prompt
+      # (anthropics/claude-code-action#1003), so the prompt asks Claude
+      # to invoke the skill through the Skill tool instead.
+      - uses: anthropics/claude-code-action@d535f5172dec02b204866b393d6b20b9b2aaf98d # v1.0.266
+        id: review
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          prompt: >-
+            Use the Skill tool to run the code-review skill with the
+            arguments "high --comment ${{ github.event.pull_request.number }}".
+          claude_args: >-
+            --model claude-sonnet-5-5
+            --allowedTools
+            "Skill,Read,Grep,Glob,Agent,Bash(git log:*),Bash(git show:*),Bash(git diff:*),Bash(git blame:*),Bash(gh pr view:*),Bash(gh pr diff:*),Bash(gh pr comment:*),Bash(gh api:*),mcp__github_inline_comment__create_inline_comment"
+
+      # A run in which Claude never invokes the skill still exits
+      # successfully, with no review posted. Fail the job when the
+      # execution log holds no Skill tool call.
+      - name: Check that the review ran
+        env:
+          EXECUTION_FILE: ${{ steps.review.outputs.execution_file }}
+        run: |
+          if ! jq -e '[.[] | select(.type == "assistant")
+                | .message.content[]?
+                | select(.type == "tool_use" and .name == "Skill")]
+                | length > 0' "$EXECUTION_FILE" > /dev/null; then
+            echo "::error::Claude did not invoke the code-review skill"
+            exit 1
+          fi
+
+      # The action hides Claude's output, so a failed run otherwise
+      # leaves no error text. Print only the final result message.
+      - name: Show why the review failed
+        if: failure() && steps.review.outputs.execution_file != ''
+        env:
+          EXECUTION_FILE: ${{ steps.review.outputs.execution_file }}
+        run: |
+          jq -r '.[] | select(.type == "result") | .result // empty' \
+            "$EXECUTION_FILE"