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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bitwarden-code-review:classifying-review-findingsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
| Emoji | Category | Criteria |
| Emoji | Category | Criteria |
|---|---|---|
| ❌ | CRITICAL | Will break, crash, expose data, or violate requirements |
| ⚠️ | IMPORTANT | Missing error handling, unhandled edge cases, could cause bugs |
| ♻️ | DEBT | Duplicates patterns, violates conventions, needs rework within 6 months |
| 🎨 | SUGGESTED | Measurably improves security, reduces complexity by 3+, eliminates bug classes |
| ❓ | QUESTION | Requires human knowledge - unclear requirements, intent, or system conflicts |
ALWAYS use hybrid emoji + text format for each finding (if multiple severities apply, use the most severe: ❌ > ⚠️ > ♻️ > 🎨 > ❓):
Verify ALL three:
If any answer is "no" or "unsure" → DO NOT classify as a finding.
Only suggest improvements that provide measurable value:
Provide concrete metrics:
If you can't measure the improvement, don't suggest it.
npx claudepluginhub bitwarden/ai-plugins --plugin bitwarden-code-reviewPerforms production-level PR reviews using a consultant agent and 10-category framework prioritizing correctness, logic errors, type safety, and observability.
Delivers one-shot structured code reviews for PRs, diffs, files, or functions. One line per issue: L<line>: SEVERITY problem. Fix: exact change. Severities: BUG, RISK, SEC, PERF, NIT, Q. No summaries.
Coordinates parallel code reviews across security, performance, architecture, testing, and accessibility dimensions with finding deduplication, severity calibration, and consolidated reporting.