By coldingcode
Generate complete Ruankao (软考) system architect mock exams from PDF materials and web trends, including 75 MCQs, 6 short answers, and essays; compile into interactive HTML candidate interfaces with timers and navigation; auto-grade JSON submissions via AI for detailed scores, feedback, and pass estimates.
软考(计算机技术与软件专业技术资格考试)备考工具 - 自动生成选择题、问答题、论文题并提供智能评分服务。
ruankao-agent/
├── .claude-plugin/
│ └── plugin.json # 插件清单
├── commands/
│ ├── generate.md # 生成试卷命令
│ └── grade.md # 评分命令
├── agents/
│ ├── mcq-agent.md # 选择题生成智能体
│ ├── essay-agent.md # 问答题生成智能体
│ ├── paper-agent.md # 论文题生成智能体
│ ├── assemble-agent.md # 试卷汇编智能体
│ └── grader-agent.md # 评分智能体
├── marketplace.json # 插件市场配置(用于发布)
├── output/ # 生成文件目录
│ # 考生可见
│ ├── index.html # 答题界面
│ ├── exam_data.js # 试题数据(JS 格式,解决本地加载问题)
│ ├── mcq_questions.json # 选择题(无答案)
│ ├── essay_questions.json # 问答题(无答案)
│ ├── paper_question.json # 论文题(无评分标准)
│ ├── exam_manifest.json # 考试元数据
│ # 保密存储
│ ├── mcq_answers.json # 选择题答案
│ ├── essay_scoring_guide.json # 问答题评分标准
│ ├── paper_scoring_guide.json # 论文题评分标准
│ ├── exam_context_pack.json # 评分上下文包
│ ├── answers.json # 考生作答(导出)
│ ├── score_report.json # 评分数据
│ └── score_report.html # 评分报告
├── README.md
├── ARCHITECTURE.md # 架构设计文档
├── LICENSE # MIT 许可证
└── .gitignore
在 Claude Code 中执行以下两条命令即可:
# 1. 添加 GitHub 市场(首次使用需要配置)
/plugin marketplace add coldingcode/ruankao-agent
# 2. 安装插件
/plugin install ruankao-agent
# 3.加载插件
/plugin reload
安装完成后,运行 /plugin list 验证,看到 ruankao-agent 即表示安装成功。
在 Claude Code 中执行:
/generate
命令将依次调用以下智能体:
mcq-agent - 生成 75 道选择题(输出:试题 + 答案分离)essay-agent - 生成 6 道问答题(输出:试题 + 评分标准分离)paper-agent - 生成 1 道论文题(输出:试题 + 评分标准分离)assemble-agent - 汇编生成 HTML 答题界面 + exam_manifest.json + context_pack/generate 生成试卷index.html 和 exam_data.js 在同一目录下output/index.html 进行答题answers.json考生完成作答并导出后:
/grade
或指定作答文件:
/grade --answers output/ruankao_answers_xxx.json
评分命令将:
exam_id 一致性(防止试卷错配)exam_context_pack.json(含答案和评分标准)score_report.json 和 score_report.html评分完成后会生成:
output/score_report.json - 结构化评分数据output/score_report.html - 可视化的评分报告插件支持以下配置:
| 配置项 | 说明 | 默认值 |
|---|---|---|
pdf_source_path | PDF 复习资料路径(选择题生成用) | 需手动指定 |
exam_category | 考试类别 | "系统架构设计师" |
✅ 考生可见(无答案):
├── index.html
├── exam_data.js
├── mcq_questions.json
├── essay_questions.json
└── paper_question.json
🔒 保密存储(评分时使用):
├── mcq_answers.json
├── essay_scoring_guide.json
├── paper_scoring_guide.json
└── exam_context_pack.json
exam_manifest.json 包含:
exam_id 标识试卷版本评分时会验证 exam_id 一致性,防止试卷错配。
在 agents/ 目录下创建新的 .md 文件,按照以下格式:
---
description: 智能体描述
version: 1.0.0
---
# 智能体名称
## 角色定位
...
## 任务目标
...
## 输出格式
...
编辑 agents/assemble-agent.md 中的模板结构,或创建自定义模板。
使用以下命令查看插件加载详情:
claude --debug
git checkout -b feature/AmazingFeature)git commit -m 'Add some AmazingFeature')git push origin feature/AmazingFeature)MIT License - 详见 LICENSE 文件
感谢所有为软考备考工具做出贡献的开发者!
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub coldingcode/ruankao-agent --plugin ruankao-agentHarness 多智能体 Web 应用构建插件 v3。Command 作为 Harness 主控,以 claude -p 独立进程调度各智能体。技术栈固定:Spring Boot 3 后端 + React 前端,内嵌 SQLite,无外部依赖。
CCAF (Claude Certified Architect – Foundations) mock-exam readiness gate. Assembles a 60-question case-study-framed mock with machine-enforced domain weighting — every question generated fresh per attempt and independently verified — administers it 4 per screen with resumable progress, and scores it on the real 100–1000 band with a 720 pass line plus a per-domain breakdown. Run /ccaf:mock-exam.
Interactive learning companion — creates personalized learning plans, quizzes with adaptive difficulty, and tracks progress across sessions
Adaptive technical tutoring skill that builds a persistent knowledge graph and learner profile across sessions
한국어 기술 문서 작성 스킬
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.