#code-review
12 skills & prompts · 2 tools · 9 MCP servers · 1 articles
Skills & prompts
Adversarial code-review skill for Claude
A Claude skill that reviews a diff by trying to refute each finding before reporting it.
Refactor-with-tests recipe for Cursor
A Cursor recipe that writes a characterization test before each refactor step.
Conventional-commit writer for Claude
Turns a staged diff into a clean Conventional Commits message — correct type, tight subject, useful body.
Review-before-apply skill for Codex CLI
Forces Codex CLI to show the diff, review its own changes, run focused validation, and list uncertainty before you keep the patch.
Security-review skill for Claude
A structured security pass over a diff — checks the OWASP-relevant classes, ranks by exploitability, and shows a repro.
Test generation loop for GitHub Copilot
Use /setupTests, /tests, and /fixTestFailure in a red-green loop instead of asking Copilot to “add some tests” and hoping for the best.
Code review guardrails for GitHub Copilot
A review skill that makes Copilot focus on concrete behavior changes, missing tests, and repo instructions instead of generic style chatter.
auto-test-code
当用户明确要求"测试代码"、"运行代码审查"或"进行代码自检"时使用。通过多轮 A 轮批判性代码审查 + B 轮代码质量原则检查，系统化发现、记录、修复程序代码中的问题，并将计划/过程/结果统一沉淀到目标代码根目录的 `.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-code/{yyyy-mm-dd-hh-mm}/output/tests/` 隔离工作区。⚠️ 不适用：用户只是想优化功能（应直接修改）、只是询问代码问题（应直接回答）、没有明确"测试代码"意图。
requesting-code-review
完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。
forgejo-cli
Use when managing a Forgejo or Gitea server from the terminal: issues, pull requests, repositories, file contents, labels, milestones, releases, webhooks, user settings, or any /api/v1 endpoint through a safe generic API command. Do not use this skill for unrelated requests; rout
receiving-code-review
收到代码审查反馈后、实施建议之前使用，尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证，而非敷衍附和或盲目执行
Tools
54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more…
MCP servers
Consult a multi-model panel on contested decisions via MCP: architecture, plan review, strategy.
The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.
Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Co…
Evidence-grounded repository audit CLI - deterministic scanner, MCP server, live dashboard, and a GitHub Action that posts PR diffs.
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context…
Articles
Prompt injection is not an XSS problem
Sanitizing output protects your page. It does nothing for an agent that reads a poisoned README and then runs a command. A practical model of the threat, and what actually helps.