跳到正文
cccskills
免费在 GitHub 公开

review

Perform a direct five-axis code review across correctness, security, performance, readability, and maintainability. Use when the user asks for `/review`, PR review, security review, pre-merge review, production readiness review, or blocking issue assessment.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Review

Overview

Use this skill for code-review work. Prioritize bugs, behavioral regressions, security risks, performance issues, and missing tests. Findings come first, ordered by severity, with concrete file and line references whenever possible.

Workflow

  1. Inspect the requested diff, files, branch, or pull request context.
  2. Review across five axes:
    • Correctness.
    • Security.
    • Performance.
    • Readability.
    • Maintainability.
  3. Check whether tests cover the changed behavior and important failure modes.
  4. Keep feedback specific and actionable; avoid broad style commentary unless it affects maintainability or correctness.
  5. Flag issues by severity:
    • Blocking: should not ship.
    • High: likely bug, security issue, or serious regression.
    • Medium: meaningful risk or missing coverage.
    • Low: small maintainability or clarity improvement.
  6. If no issues are found, say so clearly and mention residual test gaps or assumptions.

Output Pattern

  1. Findings first, ordered by severity.
  2. Open questions or assumptions.
  3. Brief change summary only after findings.
  4. Tests or verification reviewed.

Example Prompts

  • /review - Review this pull request. Flag anything that affects security, performance, or will be hard to maintain in 6 months. Be direct about blocking issues.
  • /review - Audit this API endpoint handler for security issues. Check for injection risks, missing auth checks, improper error handling, and data exposure.
  • /review - This is going to production tomorrow. Do a final review focused only on breaking changes, regressions, and anything that could cause an incident.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Design, analyze, and document A/B tests for conversion, onboarding, pricing, lifecycle, and product experiments. Use when the user asks for `/ab-test-setup`, experiment design, sample size, statistical significance, A/B test analysis, ICE-scored test backlogs, or avoiding common testing mistakes.

中文简介正在准备中。当前显示原文说明。

eigent-ai/agent-skills242026年10月14日 更新

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

中文简介正在准备中。当前显示原文说明。

eigent-ai/agent-skills242026年10月14日 更新

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

中文简介正在准备中。当前显示原文说明。

eigent-ai/agent-skills242026年10月14日 更新

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

中文简介正在准备中。当前显示原文说明。

eigent-ai/agent-skills242026年10月14日 更新

Transform git commit history into polished user-facing changelogs and release notes. Use when the user wants a CHANGELOG.md from a version tag or date range, weekly product updates, app store release notes, or Keep a Changelog formatted output with internal noise filtered out.

中文简介正在准备中。当前显示原文说明。

eigent-ai/agent-skills242026年10月14日 更新

Full legal plugin suite for commercial contract review, privacy/DPA analysis, and AI governance vendor reviews. Use when the user invokes /commercial-legal:review, /privacy-legal:dpa-review, /ai-governance-legal:vendor-ai-review, renewal tracking, DSAR responses, or EU AI Act triage.

中文简介正在准备中。当前显示原文说明。

eigent-ai/agent-skills242026年10月14日 更新

查看 eigent-ai 的全部技能

报告此技能的问题