sero-code-review
Review a PR, a branch, or a diff in the Sero monorepo and post the findings. Use when the user asks to review code, review a PR, re-review after new commits, check a branch before merge, or double-check an earlier review. Trigger on phrases like "review this PR", "review the delt
供给资产档案
编程与开发 Agent
代码审查、仓库分析、测试、CI、GitHub、DevOps 与开发工作流 Skill。
场景
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
适配 Agent
Claude Code + CLI + Codex
适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。
安装
就绪
npx skills add sero-labs/sero --skill sero-code-review
维护状态
新鲜
距上次推送 3 天
风险
需审查
The skill is tightly coupled to the Sero monorepo and its specific CI workflows, which may limit reuse outside that repository, but that is acceptable for a repository-scoped skill.
GitHub 质量
19
59/100 质量 · 71/100 信任
覆盖标签
审查说明
The skill is tightly coupled to the Sero monorepo and its specific CI workflows, which may limit reuse outside that repository, but that is acceptable for a repository-scoped skill. · Low GitHub adoption signal
Agent 采用评分卡
一眼查看信任、审计与安装准备度
这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。
质量
有潜力有用的候选项,但采用前应与替代方案比较。
信任
仅限沙盒有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
审计
需审查对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。
OpenAgentSkill 信任评分 v5
安装前需人工审查
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
Stars
19 个 GitHub Stars
仓库活跃度
19 个 Star,1 个 Fork
维护状态
距上次推送 3 天
许可证
Apache-2.0
安装
npx skills add sero-labs/sero --skill sero-code-review
安装安全性
标准软件包或运行时安装路径
权限范围
文件系统或文档访问
Agent 结果
暂未有 Agent 结果数据
文档
Usable metadata, review docs
风险摘要
生产前审查
- The skill is tightly coupled to the Sero monorepo and its specific CI workflows, which may limit reuse outside that repository, but that is acceptable for a repository-scoped skill.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 19 GitHub stars
安装准备度
安装路径可用
- 安装路径可用
- 仓库证据可用
- 已声明许可证
- 暂无 Agent 验证结果证据
Agent 可读元数据
这个 Skill 的机器可读决策数据。
使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。
适用任务
- GitHub automation 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
- Inspect repository metadata
适用 Agent
安装决策
- 命令
- npx skills add sero-labs/sero --skill sero-code-review
- 策略
- 审查
- 人工审查
- 是
信任与风险
- 信任
- 63/100
- 审计
- 76/100
- 风险级别
- 需审查
结果闭环
- 端点
- /api/agent/outcome
- 事件 ID
- resolve
- 结果
- 5
不适用场景
- 需要厂商支持 SLA 的团队
- production agents without a repository review
- Low GitHub adoption signal
- The skill is tightly coupled to the Sero monorepo and its specific CI workflows, which may limit reuse outside that repository, but that is acceptable for a repository-scoped skill.
- Quality score needs review
替代 Skill
Frontend Design
171.1K Stars
npx skills add anthropics/skills --skill frontend-design
替代 Skill
Taste Skill: Anti-Slop Frontend
79.4K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
替代 Skill
Canvas Design
171.1K Stars
npx skills add anthropics/skills --skill canvas-design
替代 Skill
Anthropic Brand Guidelines
171.1K Stars
npx skills add anthropics/skills --skill brand-guidelines
Agent 安全 v2
60/100 · 安装前审查
可用候选,但 Agent 在安装前应展示权限与审计说明。
在真实工作区安装前需要人工批准。
中
网络访问
Skill 可能访问远程页面、API、仓库或外部服务。
中
文件系统访问
Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。
- The skill is tightly coupled to the Sero monorepo and its specific CI workflows, which may limit reuse outside that repository, but that is acceptable for a repository-scoped skill.
安装目标
在你的 Agent 工作流中安装此 Skill
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install sero-labs-sero-code-reviewAgent 解析计划
让 Agent 在安装前验证匹配度。
Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。
打开 JSON
/api/agent/resolve?task=Use%20sero-code-review%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve 文本
/api/agent/resolve?task=Use%20sero-code-review%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
安装交接
/api/skills/sero-labs-sero-code-review/install
Agent 应检查
- 从 Resolve API 检查任务匹配与替代方案。
- 检查审计评分、信任评分和安全策略警告。
- 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。
复制提示词
Task: Use sero-code-review in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20sero-code-review%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/sero-labs-sero-code-review/install
Install command: npx skills add sero-labs/sero --skill sero-code-review
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent 交接
把安装路径交给 Agent,而不是再给一个目录页。
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
安装交接
/api/skills/sero-labs-sero-code-review/install
LLM 文本格式
/api/skills/sero-labs-sero-code-review/install?format=text
寻找替代方案
/api/skills/search?q=sero-code-review&limit=3
Agent 提示词
Use sero-code-review for this task. Review https://www.openagentskill.com/api/skills/sero-labs-sero-code-review/install, then install with: npx skills add sero-labs/sero --skill sero-code-reviewRegistry 元数据
用于自动选择 Skill 的 Agent 可读档案。
本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。
Agent 决策面板
Fallback candidate for GitHub automation
先用此 Skill 做原型验证,并保留备选方案。
栈中角色
备选候选
主要匹配
GitHub automation
信任标签
先做原型验证
安装路径
命令已就绪
适用场景
- GitHub automation 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
证据
- 仓库近期活跃
- 已提供安装命令或 GitHub 仓库
- 59/100 质量档案
- 5 个 OpenAgentSkill 交互事件
先审查
- Low GitHub adoption signal
- The skill is tightly coupled to the Sero monorepo and its specific CI workflows, which may limit reuse outside that repository, but that is acceptable for a repository-scoped skill.
实施路径
- 1在沙盒 Agent 中安装它,并端到端完成一次GitHub automation任务。
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
信任档案
仅限沙盒
有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
GitHub 采用度
修复19 个 GitHub Stars
Star/Fork 活跃度
修复19 个 Star,1 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过距上次推送 3 天
许可证清晰度
通过Apache-2.0
积极信号
- AI 审查已通过
- 安装路径可用
- 仓库证据可用
- 近期维护的仓库
- 安装命令未发现明显高风险模式
- 结果闭环已就绪,但需要首次真实 Agent 运行
安装前审查
- The skill is tightly coupled to the Sero monorepo and its specific CI workflows, which may limit reuse outside that repository, but that is acceptable for a repository-scoped skill.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 19 GitHub stars
- Stars/forks activity: 19 stars, 1 forks; issue activity unavailable in current metadata
- 暂未有真实 Agent 结果报告
- 无人值守安装前需要人工审查
建议操作
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
质量档案
有潜力 适用于 Agent 工作流的候选
有用的候选项,但采用前应与替代方案比较。
工作流匹配
在这些场景使用此 Skill
Manage repositories
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Operate web apps
Browser automation
I need my agent to control a browser, fill forms, and verify web app workflows.
工作流匹配
加入完整工作流
Inspect, patch, and verify code
Coding review agent
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Operate and verify web apps
Browser QA agent
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Find, compare, and synthesize
Research report agent
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
替代方案短名单
安装前对比
可能适合该任务的相近 Skill。
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Canvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Anthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
概览
--- name: sero-code-review description: | Review a PR, a branch, or a diff in the Sero monorepo and post the findings. Use when the user asks to review code, review a PR, re-review after new commits, check a branch before merge, or double-check an earlier review. Trigger on phrases like "review this PR", "review the delta", "check the changes", "double check it", or any request that ends in review findings. Use this in place of the built-in code-review skill. ---
# Sero Code Review
Applies to every PR review, branch review, and delta re-review.
These rules exist because unverified findings and split review rounds waste more time than the review saves.
## 0. The goal is a green light
A review succeeds when the branch ships. It does not succeed by finding more things. Each round must move towards a verdict, never away from one.
- Give a clear verdict every time: **green** (ship it) or **red** (do not ship, and here is exactly what blocks it). Never end a review with an open-ended list and no call. - Only a correctness, data-loss, or security defect can hold a red light. Style, taste, "could be cleaner", and hypothetical edge cases never block a merge. - Everything else is a **non-blocking note**. Say so plainly, in the same breath, so nobody has to guess whether it must be fixed. - When the blocking findings are fixed, call it green. Do not replace them with a fresh tier of smaller findings you did not think worth raising before. - Later rounds must shrink. If a re-review produces more blocking findings than the round before it, the earlier round was not done properly — say that instead of quietly extending the list. - No finding at all is a valid and good result. Say "green, nothing found." - The verdict covers the **code**. Merge blockers that are not code defects — the branch is behind its base, CI never ran, `packages/*` changed and needs republishing — go in their own short list under the verdict. Green code with an unmergeable branch is still green code; do not blur the two.
## 1. Verify before you report
- Read the mechanism in the source. Do not infer it. If a finding says "this function returns null", "A runs before B", or "this value is stale", open the file and read the lines that prove it. - Quote the `file:line` you read, not the one you guessed. - A finding you cannot prove goes in a separate **Suspected** list, marked unproven — or it is not reported. Never present an inferred cause as a fact. - State what you ran (`pnpm typecheck`, test suites, line counts) and what you could not check. Never imply coverage you do not have. - Green checks on a **draft** PR prove almost nothing. `.github/workflows/test.yml` skips `Detect changes`, `Fast checks` and `PR Gate` while the PR is a draft, so the rollup can read all-green with no tests run at all. Read the job conclusions (`gh pr view <pr> --json statusCheckRollup`) and treat `SKIPPED` as "not run". Run the touched suites locally and say so.
## 2. Sweep the fault class
- For every defect, search the sibling paths for the same pattern before you close it out. Error handling, guards, and races cluster: if one branch has no error surface, check the other branches in the same component. - Do the same for every fix on a re-review. A fix can leave the identical gap in the path beside it, and can add a new fault. - Re-read changed logic in full. A green test suite does not clear a concurrency or ordering change.
## 3. One review, one comment
- Post to the PR yourself as part of the job. Do not ask first. - Keep **one** comment per PR. Update it with `gh pr comment <pr> --edit-last --create-if-none --body-file <file>`. Never stack a comment per round — the PR holds one current review, not a pile of rounds and corrections. `--edit-last` on its own fails when you have not commented on that PR yet, and it edits *your* last comment only, so a reply from someone else in between does not break it. - A delta re-review opens with the status of every previous finding (fixed / not fixed / changed), then the new ones. - Lead with the verdict, then the blocking findings, then the non-blocking notes.
## 4. Second pass before posting
Perform a fresh second pass with the review tools available in the current environment. Re-read the changed logic and verify each proposed finding against the source. Do not depend on a specific model, agent, or editor-only skill.
Reconcile the second pass with the first **before** the comment goes up. A wrong finding corrected in session costs nothing; corrected on the PR it costs a round trip and the reader's trust.
## 5. Scope
- Review when the branch is ready, not on every push, unless asked for a mid-flight pass. - Check type safety, the 500 LOC file limit, and whether `apps/docs-site` and `docs/prototypes` needed an update. - Do not let review feedback expand the PR scope beyond the users original goal. Address real shortcomings but avoid scope creep
技术详情
- 版本
- 1.0.0
- 许可证
- Apache-2.0
- 最近更新
- 2026年8月19日
- 发布时间
- 2026年8月19日
决策摘要
备选候选
仓库近期活跃
Agent 验证证据
Agent 验证证据
来自解析、审查、安装和一次小范围运行后的结果报告。
- 成功率
- —
- 近期失败
- —
- 结果
- 0
- 输出质量
- —
- 失败
- 0
- 不相关
- 0
- 安装次数
- 0
- 风险拦截
- 0
- 需要配置
- 0
- 生产环境
- 0
暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。
增长闭环
分享工具包
为 sero-code-review 准备的场景化草稿,可手动发布到 X。
A practical pick for design or creative work: sero-code-review: Review a PR, a branch, or a diff in the Sero monorepo and post the findings. Use when the user asks to review code, review... 19 stars https://www.openagentskill.com/skills/sero-labs-sero-code-review?ref=x
可选:带安装命令的回复
Listing + install path for sero-code-review: https://www.openagentskill.com/skills/sero-labs-sero-code-review?ref=x Install: npx skills add sero-labs/sero --skill sero-code-review
收录来源
Registry 收录
此列表来自公开来源,维护者认领获批前不会标记为官方。
- 创作者
- sero-labs
- 收录方
- OpenAgentSkill 社区索引
归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。
认领此 Skill所有者认领
认领此 Skill 页面
这条 Registry 收录 列表归属于 sero-labs,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。
创作者外链工具包
将证据徽章加入你的 README
在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。
[](https://www.openagentskill.com/skills/sero-labs-sero-code-review)
[](https://www.openagentskill.com/skills/sero-labs-sero-code-review)
[](https://www.openagentskill.com/skills/sero-labs-sero-code-review/audit)
[](https://www.openagentskill.com/skills/sero-labs-sero-code-review)作者
sero-labs
@sero-labs
平台适配
健康信号
- GitHub Stars
- 19
- 质量评分
- 32/100
- 最近 GitHub 推送
- 2026年8月19日
- 框架提示
- 未知
- OpenAgentSkill 浏览量
- 5
- 复制安装命令
- 0
- 跳转点击
- 0
社区信号
告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。
信任与安全
仅限沙盒
- GitHub 采用度19 个 GitHub Stars修复
- Star/Fork 活跃度19 个 Star,1 个 Fork; 当前元数据中没有议题活跃度信息修复
- 近期维护距上次推送 3 天通过
- 许可证清晰度Apache-2.0通过
- README/SKILL.md 完整度公开元数据需要更完整的 README/SKILL.md 上下文信息
- 依赖与运行时风险公开元数据中未发现主要依赖风险提示通过
相关 Skill
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
171.1K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
79.4K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
171.1K StarsAnthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
171.1K Stars