fix(skills): fix the regexp in the update_docs.js script

[boneskull]

Fixed the regexp in update_docs.js script.

Motivation and Context

This script was downloading 0 files.

Evidently they changed the URL scheme in llms.txt has changed; claude-code is no longer in the URL.

After this change, the script fetches 95 docs.

How Has This Been Tested?

Manually

Breaking Changes

No

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update

Checklist

• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed

Additional context

Summary by CodeRabbit

• Chores
  • Updated documentation collection patterns to include additional pages from the documentation site.

[coderabbitai]

Walkthrough

The regex pattern in the documentation update script was modified to broaden URL matching from specifically claude-code subdirectories to any path under en/docs, expanding which Markdown pages are collected from llms.txt without altering surrounding logic.

Changes

Cohort / File(s)	Summary
Regex pattern expansion skills/working-with-claude-code/scripts/update_docs.js	Modified URL matching regex from /https:\/\/docs\.claude\.com\/en\/docs\/claude-code\/[^\s)]+\.md/g to /https:\/\/docs\.claude\.com\/en\/docs\/[^\s)]+\.md/g, removing the claude-code subpath requirement to match any documentation under en/docs

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

• Verify the broader regex pattern doesn't unintentionally match documentation files that shouldn't be included in the update
• Confirm llms.txt collection behavior aligns with the expanded scope

Poem

🐰 A regex once rigid, now flows free and wide,
From claude-code alone to docs far and deep,
Patterns now dance across broader terrain,
Catching more wisdom in llms.txt's keep! 📚✨

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately describes the main change: fixing a regex pattern in update_docs.js to resolve a bug where the script was downloading zero files due to changed URL schemes.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

Tip

📝 Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.

• Provide your own instructions using the high_level_summary_instructions setting.
• Format the summary however you like (bullet lists, tables, multi-section layouts, contributor stats, etc.).
• Use high_level_summary_in_walkthrough to move the summary from the description to the walkthrough section.

Example instruction:

"Divide the high-level summary into five sections:

1. 📝 Description — Summarize the main change in 50–60 words, explaining what was done.
2. 📓 References — List relevant issues, discussions, documentation, or related PRs.
3. 📦 Dependencies & Requirements — Mention any new/updated dependencies, environment variable changes, or configuration updates.
4. 📊 Contributor Summary — Include a Markdown table showing contributions:
   | Contributor | Lines Added | Lines Removed | Files Changed |
5. ✔️ Additional Notes — Add any extra reviewer context.
   Keep each section concise (under 200 words) and use bullet or numbered lists for clarity."

Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later.

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

skills/working-with-claude-code/scripts/update_docs.js (1)

17-17: Consider updating names and comments to reflect the broader scope.

While the regex fix is correct, the constant name CLAUDE_CODE_PATTERN, function name getClaudeCodeUrls(), and various comments (lines 6, 40, 85, 87) still reference "Claude Code" specifically. Since the pattern now matches all documentation under /en/docs/, consider renaming to better reflect this broader scope (e.g., DOCS_PATTERN, getDocsUrls()).

Also applies to: 42-42

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 6ec1473 and 4eb9525.

📒 Files selected for processing (1)

• skills/working-with-claude-code/scripts/update_docs.js (1 hunks)

🔇 Additional comments (1)

skills/working-with-claude-code/scripts/update_docs.js (1)

17-17: LGTM! The regex fix correctly addresses the URL scheme change.

The updated pattern successfully broadens the match criteria from specifically /claude-code/ subdirectories to any path under /en/docs/, which resolves the zero-file download issue.