菜单
Run structured code/security review for local, branch, or commit diffs with explicit RED-safe routing.
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
| name | autoreview |
| description | Run structured code/security review for local, branch, or commit diffs with explicit RED-safe routing. |
Use this skill for AI-assisted code review of local, branch, or commit changes when the reviewed content is safe for the selected reviewer engine.
This local Ralph variant changes the upstream defaults:
--web-search.--include-untracked.git fetch is disabled by default and requires --fetch.--parallel-tests is explicit trusted shell input from the operator.--review-pass N; --review-total M
defaults to 2 and is capped at 10.Never run an open-ended fix/review loop.
--review-pass N --review-total M.python3 skills/autoreview/scripts/autoreview.py --mode auto --dry-run
python3 skills/autoreview/scripts/autoreview.py --mode local --review-pass 1 --review-total 10
python3 skills/autoreview/scripts/autoreview.py --mode branch --base origin/main --review-pass 1 --review-total 10
python3 skills/autoreview/scripts/autoreview.py --mode branch --base origin/main --review-pass 10 --review-total 10
python3 skills/autoreview/scripts/autoreview.py --mode commit --commit HEAD --review-pass 1 --review-total 10
Use web search only for public/GREEN context:
python3 skills/autoreview/scripts/autoreview.py --mode branch --web-search --sensitivity GREEN --review-pass 1 --review-total 10
Keep this skill repo-local until review passes. Promote the whole
skills/autoreview/ directory to the global skill root only after explicit user
approval.
Improve, audit, simplify, rewrite, or migrate prompts, tool descriptions, agent instructions, and prompt stacks for GPT-5.6 Sol or the GPT-5.6 family. Use for outcome-first prompt design, autonomy boundaries, tool routing, PTC, grounding, verbosity, reasoning effort, and prompt evals.
Apply a deep, design-minded engineering workflow for complex work that needs careful planning, iteration, and simplification.
Use when preparing or running a Claude CLI agentic engineering review through claude -p for repository audits, architecture analysis, system design, security review, large refactors, specs, RFCs, or evidence-grounded long-form engineering analysis.
Use when preparing or running a ZCode GLM-5.2 agentic builder workflow through zcode --prompt for fast implementation, iterative code generation, focused fixes, and validation on an existing repository.
Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, red-team reasoning, or Z.ai and MiniMax cross-checks through the Ralph MCP router.
Review and adjudicate Bugbot, Cursor, Seer, and similar automated PR feedback with local evidence before accepting, fixing, or dismissing findings.