bitwarden/ai-plugins

Analyzes git commits and changes within a timeframe or commit range, providing structured summaries for code review, retrospectives, work logs, or session documentation.

Use this skill when validating ANY potential code review finding. Apply BEFORE classifying to verify the finding is real; can you trace incorrect behavior, is it handled elsewhere, and are you certain about framework semantics? If any answer is no, DO NOT create the finding.

Use this skill when categorizing code review findings into severity levels. Apply when determining which emoji and label to use for PR comments, deciding if an issue should be flagged at all, or classifying findings as CRITICAL, IMPORTANT, DEBT, SUGGESTED, or QUESTION.

Use this skill when posting inline comments to GitHub pull requests. Apply when formatting comments following Bitwarden engineering standards with severity emojis, clear explanations, and actionable suggestions. Use after findings are classified and ready to post. DO NOT USE when posting summary comments.

Use this skill when posting the final summary comment after all inline comments are posted. Apply as the LAST step of code review after all findings are classified and inline comments are complete. Detects context (GitHub sticky comment, new comment, or local file) and routes output accordingly.

Reviews Claude configuration files for security, structure, and prompt engineering quality. Use when reviewing changes to CLAUDE.md files (project-level or .claude/), skills (SKILL.md), agents, prompts, commands, or settings. Validates YAML frontmatter, progressive disclosure patterns, token efficiency, and security best practices. Detects critical issues like committed settings.local.json, hardcoded secrets, malformed YAML, broken file references, oversized skill files, and insecure agent tool access.

Use this skill when re-reviewing a PR that already has comments or when responding to developer changes after initial review. Apply when PR threads exist or when reviewing force-pushed commits. Handles incremental reviews, detects addressed feedback, avoids duplicate comments, and focuses only on newly introduced issues.