菜单
Run a cross-model code review using both opus and sonnet in parallel, then merge and deduplicate findings into a combined summary. Use when the user says cross review, dual review, cross-model review, review with both models, or wants a thorough second-opinion review of changes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Quick codebase exploration to understand how something works. Use when the user says how does X work, explain the flow, where is X handled, show me how, walk me through, or needs to understand code before making changes.
Fix all issues from a cross-validation review summary. Use when the user says fix issues, fix these, fix the review findings, address the issues, or after /implement produces a cross-validation summary.
Implement a validated feature plan task-by-task using Backend Architect and Frontend Developer agents, with progress tracking and user confirmation between tasks. After all tasks complete, automatically runs cross-model review (opus + sonnet). Use when the user says implement, build this, implement the plan, start implementation, or after /plan-feature produces a validated plan.
Deep investigation and root cause analysis using the DeepDive agent workflow. Use when the user says investigate, why does this break, what is causing, debug this, find the root cause, or any request to analyze a bug or issue without immediately writing a fix.
Run the three-phase Feature Planner validation before implementing a feature. Use when the user says plan feature, plan a new feature, I want to add, or any request for structured feature planning with edge case and risk analysis.
Code review using Clean Code Architect principles. Reviews staged changes, recent commits, or specific files for quality, security, and maintainability. Use when the user says review, review my code, check this, code review, or before committing significant changes.
| name | cross-review |
| description | Run a cross-model code review using both opus and sonnet in parallel, then merge and deduplicate findings into a combined summary. Use when the user says cross review, dual review, cross-model review, review with both models, or wants a thorough second-opinion review of changes. |
git branch --show-currentgit diff --cached --statgit diff --statgit log --oneline -5Run a cross-model code review using both opus and sonnet to catch blind spots.
Target: $ARGUMENTS
If no target specified, review all staged and unstaged changes. If no changes exist, review the most recent commit.
Determine the review scope:
git diff HEAD~1)Collect the full list of files and changes to review.
Use the Agent tool to launch TWO review agents in parallel (both in the same message):
Agent A (opus): Launch a general-purpose agent with model: opus. Provide it the list of files/changes and instruct it to review for:
It must produce a structured list of issues with severity, file path, line number, and description.
Agent B (sonnet): Launch a general-purpose agent with model: sonnet. Same files, same review criteria, independent review. This provides a second perspective.
After both agents complete:
## Cross-Review Summary
**Scope:** [what was reviewed]
**Models:** opus + sonnet
### Must Fix (found by both models)
- [Issue] — `file:line` — [description]
### Should Fix (found by one model)
- [Issue] — `file:line` — [found by: opus|sonnet] — [description]
### Consider
- [Suggestion] — `file:line` — [found by: opus|sonnet] — [description]
### What Looks Good
- [Positive observations agreed on by both models]
### Stats
- Total issues: X (Y must fix, Z should fix, W consider)
- Consensus issues (both models): X
- Opus-only issues: X
- Sonnet-only issues: X
### Next Step
Run `/fix-issues` to address all must-fix and should-fix items.
IMPORTANT: Do NOT ask the user whether to run either review. Both models run automatically. This is the entire purpose of this skill.