alihan/claude-cookbooks
1
0
Fork 0
mirror of https://github.com/anthropics/claude-cookbooks.git synced 2025-10-06 01:00:28 +03:00
Code Issues Packages Projects Releases Wiki Activity
Files
92579ad489e48743cfb963225d1606c83eb496b3
claude-cookbooks/.claude/commands/notebook-review.md
Stephen Grider d2cab04253 Remove duplicate model usage check from notebook-review 
The model-check command already handles model validation for all notebooks
and Python files. This eliminates duplication and improves separation of
concerns between the two commands.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-09-12 16:52:59 -06:00

1.5 KiB
Raw Blame History

allowed-tools, description
allowed-tools description
Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*) Comprehensive review of Jupyter notebooks and Python scripts

Review the changes to Jupyter notebooks and Python scripts in this PR. Please check for:

Code Quality

  • Python code follows PEP 8 conventions
  • Proper error handling
  • Clear variable names and documentation
  • No hardcoded API keys (use os.getenv("ANTHROPIC_API_KEY"))

Notebook Structure

  • Clear introduction explaining what the notebook demonstrates and why it's useful
  • Configuration instructions (how to set up API keys, install dependencies, etc.)
  • Connecting explanations between cells that help users understand the flow
  • Clear markdown explanations between code cells
  • Logical flow from simple to complex
  • Outputs preserved for educational value
  • Dependencies properly imported

Security

  • Check for any hardcoded API keys or secrets (not just Anthropic keys)
  • Ensure all sensitive credentials use environment variables (os.environ, getenv, etc.)
  • Flag any potential secret patterns (tokens, passwords, private keys)
  • Note: Educational examples showing "what not to do" are acceptable if clearly marked
  • Safe handling of user inputs
  • Appropriate use of environment variables

Provide a clear summary with:

  • ✅ What looks good
  • ⚠️ Suggestions for improvement
  • ❌ Critical issues that must be fixed

IMPORTANT: Post your review as a comment on the pull request using the command: gh pr comment $PR_NUMBER --body "your review"