setup by everyinc/compound-engineering-plugin
npx skills add https://github.com/everyinc/compound-engineering-plugin --skill setup使用平台的阻塞式提问工具(例如 Claude Code 中的 AskUserQuestion、Codex 中的 request_user_input、Gemini 中的 ask_user)向用户提出以下每个问题。如果没有结构化的提问工具可用,则将每个问题以编号列表的形式呈现,并在继续之前等待回复。对于多选问题,接受逗号分隔的数字(例如 1, 3)。切勿跳过或自动配置。
compound-engineering.local.md 的交互式设置——配置在 ce:review 和 ce:work 期间运行哪些代理。
读取项目根目录下的 compound-engineering.local.md。如果文件存在,则显示当前设置并询问:
设置文件已存在。您希望做什么?
1. 重新配置 - 从头开始再次运行交互式设置
2. 查看当前 - 显示文件内容,然后停止
3. 取消 - 保持当前设置
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
如果选择"查看当前":读取并显示文件,然后停止。如果选择"取消":停止。
自动检测项目技术栈:
test -f Gemfile && test -f config/routes.rb && echo "rails" || \
test -f Gemfile && echo "ruby" || \
test -f tsconfig.json && echo "typescript" || \
test -f package.json && echo "javascript" || \
test -f pyproject.toml && echo "python" || \
test -f requirements.txt && echo "python" || \
echo "general"
询问:
检测到 {type} 项目。您希望如何配置?
1. 自动配置(推荐)- 为 {type} 使用智能默认值。一键完成。
2. 自定义 - 选择技术栈、关注领域和审查深度。
[kieran-rails-reviewer, dhh-rails-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle][kieran-python-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle][kieran-typescript-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle][code-simplicity-reviewer, security-sentinel, performance-oracle, architecture-strategist]a. 技术栈 — 确认或覆盖:
我们应该为哪个技术栈进行优化?
1. {detected_type}(推荐)- 从项目文件自动检测
2. Rails - Ruby on Rails,添加 DHH 风格和 Rails 特定的审查代理
3. Python - 添加 Python 风格模式审查代理
4. TypeScript - 添加类型安全审查代理
仅显示与检测到的类型不同的选项。
b. 关注领域 — 多选(用户选择一个或多个):
哪些审查领域最重要?(逗号分隔,例如 1, 3)
1. 安全性 - 漏洞扫描、身份验证、输入验证(security-sentinel)
2. 性能 - N+1 查询、内存泄漏、复杂度(performance-oracle)
3. 架构 - 设计模式、SOLID 原则、关注点分离(architecture-strategist)
4. 代码简洁性 - 过度工程、违反 YAGNI 原则(code-simplicity-reviewer)
c. 深度:
审查应该有多彻底?
1. 彻底(推荐)- 技术栈审查代理 + 所有选定的关注领域代理。
2. 快速 - 技术栈审查代理 + 仅代码简洁性代理。上下文较少,速度更快。
3. 全面 - 上述所有 + git 历史记录、数据完整性、代理原生检查。
技术栈特定代理:
kieran-rails-reviewer, dhh-rails-reviewerkieran-python-reviewerkieran-typescript-reviewer关注领域代理:
security-sentinelperformance-oraclearchitecture-strategistcode-simplicity-reviewer深度:
code-simplicity-reviewergit-history-analyzer, data-integrity-guardian, agent-native-reviewer计划审查代理: 技术栈特定审查代理 + code-simplicity-reviewer。
写入 compound-engineering.local.md:
---
review_agents: [{computed agent list}]
plan_review_agents: [{computed plan agent list}]
---
# 审查上下文
在此处添加项目特定的审查说明。
这些说明会在 ce:review 和 ce:work 期间传递给所有审查代理。
示例:
- "我们大量使用 Turbo Frames —— 检查是否存在框架破坏问题"
- "我们的 API 是公开的 —— 对输入验证进行额外审查"
- "性能关键:我们在此端点上每秒处理 10k 请求"
已保存到 compound-engineering.local.md
技术栈: {type}
审查深度: {depth}
代理: {count} 个已配置
{agent list, one per line}
提示:编辑"审查上下文"部分以添加项目特定的说明。
随时重新运行此设置以重新配置。
每周安装量
174
仓库
GitHub 星标数
10.9K
首次出现
2026 年 2 月 13 日
安全审计
已安装于
codex167
opencode165
gemini-cli164
github-copilot162
amp155
kimi-cli155
Ask the user each question below using the platform's blocking question tool (e.g., AskUserQuestion in Claude Code, request_user_input in Codex, ask_user in Gemini). If no structured question tool is available, present each question as a numbered list and wait for a reply before proceeding. For multiSelect questions, accept comma-separated numbers (e.g. 1, 3). Never skip or auto-configure.
Interactive setup for compound-engineering.local.md — configures which agents run during ce:review and ce:work.
Read compound-engineering.local.md in the project root. If it exists, display current settings and ask:
Settings file already exists. What would you like to do?
1. Reconfigure - Run the interactive setup again from scratch
2. View current - Show the file contents, then stop
3. Cancel - Keep current settings
If "View current": read and display the file, then stop. If "Cancel": stop.
Auto-detect the project stack:
test -f Gemfile && test -f config/routes.rb && echo "rails" || \
test -f Gemfile && echo "ruby" || \
test -f tsconfig.json && echo "typescript" || \
test -f package.json && echo "javascript" || \
test -f pyproject.toml && echo "python" || \
test -f requirements.txt && echo "python" || \
echo "general"
Ask:
Detected {type} project. How would you like to configure?
1. Auto-configure (Recommended) - Use smart defaults for {type}. Done in one click.
2. Customize - Choose stack, focus areas, and review depth.
[kieran-rails-reviewer, dhh-rails-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle][kieran-python-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle][kieran-typescript-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle][code-simplicity-reviewer, security-sentinel, performance-oracle, architecture-strategist]a. Stack — confirm or override:
Which stack should we optimize for?
1. {detected_type} (Recommended) - Auto-detected from project files
2. Rails - Ruby on Rails, adds DHH-style and Rails-specific reviewers
3. Python - Adds Pythonic pattern reviewer
4. TypeScript - Adds type safety reviewer
Only show options that differ from the detected type.
b. Focus areas — multiSelect (user picks one or more):
Which review areas matter most? (comma-separated, e.g. 1, 3)
1. Security - Vulnerability scanning, auth, input validation (security-sentinel)
2. Performance - N+1 queries, memory leaks, complexity (performance-oracle)
3. Architecture - Design patterns, SOLID, separation of concerns (architecture-strategist)
4. Code simplicity - Over-engineering, YAGNI violations (code-simplicity-reviewer)
c. Depth:
How thorough should reviews be?
1. Thorough (Recommended) - Stack reviewers + all selected focus agents.
2. Fast - Stack reviewers + code simplicity only. Less context, quicker.
3. Comprehensive - All above + git history, data integrity, agent-native checks.
Stack-specific agents:
kieran-rails-reviewer, dhh-rails-reviewerkieran-python-reviewerkieran-typescript-reviewerFocus area agents:
security-sentinelperformance-oraclearchitecture-strategistcode-simplicity-reviewerDepth:
code-simplicity-reviewer onlygit-history-analyzer, data-integrity-guardian, agent-native-reviewerPlan review agents: stack-specific reviewer + code-simplicity-reviewer.
Write compound-engineering.local.md:
---
review_agents: [{computed agent list}]
plan_review_agents: [{computed plan agent list}]
---
# Review Context
Add project-specific review instructions here.
These notes are passed to all review agents during ce:review and ce:work.
Examples:
- "We use Turbo Frames heavily — check for frame-busting issues"
- "Our API is public — extra scrutiny on input validation"
- "Performance-critical: we serve 10k req/s on this endpoint"
Saved to compound-engineering.local.md
Stack: {type}
Review depth: {depth}
Agents: {count} configured
{agent list, one per line}
Tip: Edit the "Review Context" section to add project-specific instructions.
Re-run this setup anytime to reconfigure.
Weekly Installs
174
Repository
GitHub Stars
10.9K
First Seen
Feb 13, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex167
opencode165
gemini-cli164
github-copilot162
amp155
kimi-cli155
agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试
152,900 周安装