Add comprehensive statistical tests value set #100

	name: Claude Code Review

	on:
	pull_request:
	types: [opened, synchronize]
	# Optional: Only run on specific file changes
	# paths:
	# - "src/*/.ts"
	# - "src/*/.tsx"
	# - "src/*/.js"
	# - "src/*/.jsx"

	jobs:
	claude-review:
	# Optional: Filter by PR author
	# if: \|
	# github.event.pull_request.user.login == 'external-contributor' \|\|
	# github.event.pull_request.user.login == 'new-developer' \|\|
	# github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'

	runs-on: ubuntu-latest
	permissions:
	contents: read
	pull-requests: read
	issues: read
	id-token: write

	steps:
	- name: Checkout repository
	uses: actions/checkout@v6
	with:
	fetch-depth: 1

	- name: Run Claude Code Review
	id: claude-review
	uses: anthropics/claude-code-action@v1
	with:
	claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}

	# In v1, providing a `prompt` runs in automation mode, which does NOT
	# post a comment by default. track_progress restores the v0.x
	# "post the review as a PR comment" behavior and auto-injects PR context.
	track_progress: true

	# Prompt for the automated review (no @claude mention needed).
	prompt: \|
	Please review this pull request and provide feedback on:
	- Code quality and best practices
	- Potential bugs or issues
	- Performance considerations
	- Security concerns
	- Test coverage

	Be constructive and helpful in your feedback.

	# Args passed through to the Claude CLI. Use the `opus` alias rather
	# than a dated model id so the workflow tracks the current Opus and
	# won't 404 when a specific version is retired.
	claude_args: \|
	--model opus

Navigation Menu