Sound familiar?
When AI agents work from prompts alone, you cannot prove the plan was followed or the tests were run. This skill makes each role write its output to a file before the next stage.
When AI agents work from prompts alone, you cannot prove the plan was followed or the tests were run. This skill makes each role write its output to a file before the next stage.
This repo is a collection of 28 skills
Boss Skill - BMAD 全自动研发流水线(多 Agent 编排)You can start at any stage, but it then runs every stage after it. Stop it by saying "stop" or with --stop-after.
/boss:reviewRead-only technical review/boss:pmWrites the requirements doc prd.md/boss:architectDesigns the architecture/boss:qaCollects test evidence in qa-report.md/boss:shipDeploy onlyWritten by our team from the maker’s files, read on 2026-11-16 · echoVic/boss-skill/README.md · echoVic/boss-skill/SKILL.md
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/echovic-boss-skill)MCP servers that connect the AI to services for the same work
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
Same kind of work, ordered like the Skills list
| This one boss-skill | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | echoVic | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 28 | 1 | 1 | 1 | 1 |
| GitHub stars | 616 | 465,460 | 233,910 | 149,364 | 144,149 |
| Last code change | Nov 16, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 17, 2026 |
| License | MIT | MIT | – | Apache-2.0 | MIT |
28 skills (instruction sets) by echoVic that an AI reads and follows · not an MCP server
Install only the ones you use. Open a skill to see how to install it
If you want every one, let the AI install them in one go. Know 2 things first
Uploading to Claude on the web and apps: you need 28 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs Nov 12, 2026 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
后端API开发方法论,包括RESTful/GraphQL设计、请求验证、错误处理和安全实现
系统架构设计方法论,包含架构模式选择、系统分层、目录结构设计
No description from the maker
自动生成 CHANGELOG,基于 git 提交历史和 pipeline 产物信息,遵循 Conventional Commits 和 Keep a Changelog 规范
代码审查方法论,基于 Google Code Review、Clean Code、SOLID 等业界实践,提供分阶段审查流程、严重度分级、常见反模式识别与可执行反馈写法
竞品调研和分析方法,通过系统性分析竞品的功能、体验和策略,发现差异化机会
前端组件开发方法论,包括组件设计原则、状态管理、样式实现和性能优化
UI 组件规范方法论,基于 Material Design 3、Ant Design、Carbon Design System 等开源组件库,定义组件解剖、变体决策、状态完备性与无障碍要求
数据模型和API设计方法论,包含ERD设计、数据字典、RESTful API规范
部署流程与CI/CD配置,包含部署平台选择、部署策略和环境管理
设计系统方法论,基于 Refactoring UI、Material Design 3、HIG、Laws of UX、WCAG 等开源设计原则,指导如何建立有设计方向、可落地的设计令牌体系
设计变体模式,产出2-3个设计方案及 tradeoff 分析,供用户选择后确定最终方案
Playwright E2E 测试完整方法论,涵盖项目初始化、Page Object Model、认证复用、API Mock、视觉回归、多浏览器测试、CI 集成和调试技巧
交互规范方法论,基于 Laws of UX、Material Design Motion、HIG 等开源原则,定义加载/空状态、反馈层级、微交互、手势与无障碍交互
监控告警配置,确保系统稳定运行
产品需求文档(PRD)的标准编写格式和内容要求,确保输出完整、清晰、可执行的产品文档
深度挖掘用户需求的方法论,通过5W2H追问和需求分层模型,识别显性、隐性、潜在和惊喜需求
风险评估方法,识别项目风险并制定应对策略
No description from the maker
从CEO/战略视角进行商业价值评审,评估市场契合度、ROI、竞争优势、风险和战略对齐
任务拆解方法,将需求拆解为可执行的开发任务
技术调研方法论,通过系统性调研和对比分析,为技术选型提供数据支持
检测项目技术栈的通用方法,通过分析配置文件识别语言、框架、工具链
技术规范和最佳实践,确保代码质量和一致性
测试执行方法,包含测试框架检测、覆盖率门禁、多框架结果解析、失败分级、增量测试选择、并行执行策略
测试策略与测试金字塔原则,定义测试优先级、风险驱动测试、测试类型决策、环境与数据策略
后端测试编写指南,包括单元测试、集成测试和E2E测试的编写方法和最佳实践
用户研究方法,通过用户画像和用户旅程图,深入理解目标用户的特征、需求和行为
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Claude CodeCodex
From the maker’s README and the folders in the repo
This repo has 28 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Checking the commands · copy buttons appear once they pass
Copied from the maker’s README; it downloads and runs the maker’s code
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.