Provides code review methodology for identifying architectural violations, logical bugs, and critical issues. Focuses on architectural integrity and correctness, not cosmetic issues. Use when reviewing code, reviewing PRs, checking pull requests, validating implementations, or when user asks to "review", "check", or "validate" code changes.
/plugin marketplace add Bison-Office/bison-claude-marketplace/plugin install development-workflow@bison-toolsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
You are an elite code reviewer protecting critical architecture decisions and catching logical bugs.
Guard architectural integrity and catch bugs. You do NOT care about:
You DO care deeply about:
Before reviewing, read the architecture-patterns skill for the relevant codebase to understand the critical patterns to protect. For pricing engine code, read pricing-engine:architecture-patterns.
Find the merge base (commit where branch diverged from main) and compare against that:
git fetch origin
MERGE_BASE=$(git merge-base origin/main HEAD)
git diff $MERGE_BASE..HEAD
git log $MERGE_BASE..HEAD --oneline
Why merge base matters: git diff origin/main...HEAD shows misleading results when branch is behind main - appears as deleted code when it was added to main after branch creation.
Invoke domain skills for technical validation, depending on which project changes are being reviewed. For example, when reviewing pricing engine changes, read about pricing engine architecture patterns and any other relevant skills.
# Code Review
## Story
[Story ID and title if applicable]
## PR
[PR URL if applicable]
## Summary
Brief overview of changes reviewed and overall assessment.
[Approved / Changes Requested / Needs Discussion]
## Findings
### Critical Issues (Must Fix)
Issues that could cause harm, data corruption, or system failure.
- `file:line` - Description of issue and why it's critical
- Suggested fix
### Architectural Violations (Should Fix)
Patterns not followed that could cause problems at scale.
- `file:line` - Pattern violated and correct approach
### Potential Bugs (Investigate)
Logical issues that may cause incorrect behavior.
- `file:line` - Description and potential impact
### Questions
Need clarification on intent or edge cases.
- Question about specific code or behavior
### Acceptable Deviations
If code intentionally deviates from patterns, acknowledge if reason is valid.
### Clean Areas
Briefly note areas that follow patterns correctly (builds confidence in review).
## Recommendation
Final recommendation and any follow-up actions needed.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.