Agent Skills › vercel/eve › review

review

GitHub

提供全面的代码安全与正确性审计,适用于PR或分支差异审查。检查漏洞、副作用及构建流程,确保仅报告由变更引入的实际缺陷,并引用确切证据。

packages/eve-code/extension/skills/review/SKILL.md vercel/eve

Trigger Scenarios

PR差异审查 分支审计 深度代码审核

Install

npx skills add vercel/eve --skill review -g -y
More Options

Non-standard path

npx skills add https://github.com/vercel/eve/tree/main/packages/eve-code/extension/skills/review -g -y

Use without installing

npx skills use vercel/eve@review

指定 Agent (Claude Code)

npx skills add vercel/eve --skill review -a claude-code -g -y

安装 repo 全部 skill

npx skills add vercel/eve --all -g -y

预览 repo 内 skill

npx skills add vercel/eve --list

SKILL.md

Frontmatter
{
    "name": "review",
    "description": "Comprehensive security and correctness audit. Use for review, deep review, thermo nuclear, or thermonuclear requests and branch or PR diff audits."
}

Deep review

Give the worker subagent a self-contained audit instruction naming the repository and target ref or worktree. The worker inspects the shared checkout directly. The root agent evaluates findings and owns the final verdict.

Audit changed code and its necessary surrounding context for bugs, broken functionality, security vulnerabilities, developer-experience regressions, and feature-gate leaks. Cite repository evidence for every finding. Report only issues introduced or exposed by code added or modified in the reviewed change.

Required checks

  • Trace cross-package and runtime side effects end to end.
  • Check authorization, untrusted input, credential disclosure, destructive behavior, and bounded work.
  • Check local build and run workflows, changed environment variables, ports, networking, and required setup.
  • Verify internal or gated features remain gated.
  • Distinguish intended, well-contained breakage from accidental consequences.
  • Calibrate priority carefully; do not inflate speculative or low-impact concerns.

Never present a finding with unfinished evidence. Name the exact missing file or ref instead. Run the independent audit before reading PR discussion so existing comments do not anchor it. Afterward, the root agent may compare findings with discussion, verify each against the workspace, and report only actionable defects.

Version History

  • a6ae201 Current 2026-09-27 14:55

Same Skill Collection

.agents/skills/gh-pr-description/SKILL.md
.agents/skills/human-writing/SKILL.md
.agents/skills/technical-writing/SKILL.md
.agents/skills/test-audit/SKILL.md
packages/eve-code/extension/skills/investigate/SKILL.md
packages/eve-code/extension/skills/lookup-agent-run/SKILL.md
packages/eve-code/extension/skills/pr/SKILL.md
SKILL.md
skills/eve/SKILL.md

Metadata

Files
0
Version
a6ae201
Hash
7b813e40
Indexed
2026-09-27 14:55

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-29 19:06
浙ICP备14020137号-1