jerry-ai-dev

Autonomous spec-driven development agent. Syncs DEV_SPEC.md into chapter-based reference files, identifies the next pending task from the schedule, implements code following spec architecture and patterns, runs tests with up to 3 auto-fix rounds, and persists…

Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QA_TEST_PLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via…

基于 Modular RAG MCP Server 项目生成定制化简历项目经历。结合项目技术亮点与用户业务场景，按简历编写原则输出高质量项目描述（中英文）。Use when user says '写简历', 'resume', '简历', 'write resume', '项目经历', 'project experience', '简历项目', or asks to generate resume content based on this project.

Guide for creating effective agent skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations. Use when user says…

Autonomous spec-driven development agent. Syncs DEV_SPEC.md into chapter-based reference files, identifies the next pending task from the schedule, implements code following spec architecture and patterns, runs tests with up to 3 auto-fix rounds, and persists…

针对 Modular RAG MCP Server 项目的模拟技术面试 Agent。读取用户简历（可选），围绕三个方向进行最多 3 轮深度追问，结束后生成并持久化面试报告（含参考答案、包装识别点评、评分）。Use when user says '模拟面试', '面试练习', '帮我面试', 'mock interview', 'interview practice', '面试', '考我', '开始面试', or wants to practice interviewing about this project.

Clean and package the project for distribution. Removes __pycache__, .venv, build artifacts, data caches, logs, IDE files, coverage reports, and sanitizes API keys in config. Produces a minimal, ready-to-share codebase. Use when user says 'package', 'clean…

Interactive project learning coach via interview-style Q&A. Reads codebase and docs, dynamically generates interview questions per knowledge domain and sub-topic, conducts up to 4 follow-up rounds, scores answers, provides learning guidance with code/doc…

针对 Smart Appointment AI Agent（按摩房智能预约系统）的模拟技术面试官。融合本地真实面试题库，围绕项目介绍、多 Agent、RAG 存储/评估、LangChain 选型、延迟、Agent 评价与学习反思进行模拟面试、追问和报告生成。Use when user says '模拟面试', '面试练习', '考我项目', '按摩房项目面试', '预约系统面试', 'mock interview', or wants interview practice for this project.

Smart Appointment AI Agent（按摩房智能预约系统）项目知识点打卡/复习教练。按知识域选择或推荐知识点，结合源码与本地真实面试题库进行问答、追问、评分、参考答案讲解和进度记录。Use when user says '学习项目', '复习项目', '项目知识点打卡', '检验项目', '考我知识点', '预约系统复习', '按摩房项目复习', 'knowledge check', or wants guided project study.

基于 Smart Appointment AI Agent（按摩房智能预约系统）生成定制化简历项目经历。沿用 Modular RAG MCP Server 简历生成风格，结合项目源码、Agent/RAG/用户记忆/反思包装方向，按四段式结构输出高质量中文或英文项目描述。Use when user says '写简历', '简历项目', '项目经历', 'resume', 'write resume', '包装项目', '优化简历', '按摩房项目简历', '预约系统简历', or asks to generate…

One-shot environment bootstrapper for the Smart Appointment AI Agent. Creates a Python virtual environment, installs dependencies from requirements.txt, scaffolds a .env file with generic OpenAI-compatible LLM / embedding / OpenWeather keys, prepares the data…

阶段三：开源项目研读教学老师。扮演一位经验丰富的开源代码导读导师，带领学生系统阅读 TRL、Open-R1、SimpleRL-Zoo 三个开源项目的核心代码，从工具库到完整项目逐步深入，最终具备独立搭建 SFT+GRPO 训练 pipeline 的工程能力。触发场景：当用户说'阶段三'、'读代码'、'开源项目'、'TRL'、'Open-R1'、'code reading'、'开始阶段三'、'继续阶段三' 等与开源项目研读相关的请求时使用。

后训练理论深化教学老师。扮演一位深入浅出的研究导师，带领已有 PyTorch 基础的学生系统学习强化学习、PPO、GRPO、RLHF、SFT 等后训练核心理论，最终读懂 DeepSeek R1 论文。覆盖数学推导、代码实现、工程技巧，以及完整的「复习模式」把所有概念串成知识网。触发场景：当用户说'后训练'、'阶段二'、'学习 PPO'、'学习 GRPO'、'学习 RLHF'、'开始后训练'、'继续后训练'、'post-training'、'post training lesson'、'RL…

PyTorch 入门教学老师。扮演一位耐心的老师，带领零基础学生循序渐进学习 PyTorch，从张量基础到 Attention、Transformer、GPT 等前沿内容。每节课包含：讲解→代码练习→测验→总结。自动跟踪学习进度，支持继续学习和复习。触发场景：当用户说'学习 PyTorch'、'pytorch 教学'、'开始上课'、'继续学习'、'复习'、'下一课'、'pytorch lesson' 等与 PyTorch 学习相关的请求时使用。