Skip to content

nicholyx/ai-skills / custom/daily/code-reviewer-agent

code-reviewer-agent

Verified

代码审查专家,使用独立上下文的 subagent 执行深度代码审查,覆盖安全漏洞、性能优化和生产可靠性。当用户说「审查一下我暂存区的改动」「帮我 review 这版代码」时使用。

FileKindSize
SKILL.mdskill md1.9 KB
code-reviewer.mdmarkdown6.2 KB
evals/evals.jsonconfig1.9 KB

evals/evals.json

View on GitHub
{
  "skill_name": "code-reviewer-agent",
  "evals": [
    {
      "id": 1,
      "name": "未指定目标时默认审查暂存变更",
      "prompt": "帮我做一下代码审查",
      "expected_output": "把审查目标整理为「当前项目的 git 暂存变更(git diff --cached)」,再 spawn 一个 description 为「深度代码审查」的 subagent,model 取自 code-reviewer.md frontmatter 的 model 字段(opus),而不是默认 sonnet",
      "files": [],
      "assertions": [
        {
          "type": "contains",
          "value": "git diff --cached|暂存"
        },
        {
          "type": "contains",
          "value": "opus"
        }
      ]
    },
    {
      "id": 2,
      "name": "把完整审查规范传给 subagent",
      "prompt": "审查一下 src/auth/ 的安全问题",
      "expected_output": "只把「审查 src/auth/ 的安全问题」这层描述交给 subagent,对应目录的代码由 subagent 自己读;code-reviewer.md 的完整内容(含 OWASP 安全审查专长)与用户需求拼接后作为 prompt,不截断也不摘要",
      "files": [],
      "assertions": [
        {
          "type": "contains",
          "value": "OWASP"
        },
        {
          "type": "contains",
          "value": "审查任务"
        }
      ]
    },
    {
      "id": 3,
      "name": "审查结果按严重程度结构化输出",
      "prompt": "帮我审查一下当前分支相对 main 的改动,简单说结论就行",
      "expected_output": "仍然完整输出 subagent 返回的审查结果(不做摘要或缩写),并按严重程度/优先级组织反馈,而不是因用户说「简单说」就省略细节",
      "files": [],
      "assertions": [
        {
          "type": "contains",
          "value": "严重|优先级|Critical|High"
        },
        {
          "type": "contains",
          "value": "opus"
        }
      ]
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall